SpotlightTodAI

Oral & Spotlight papers from top AI conferences

GitHub Buy Me A Coffee

Paper of the day ICLROral1 Oct 2026

Structured Flow Autoencoders: Learning Structured Probabilistic Representations with Flow Matching

A framework that composes any probabilistic graphical model with flow matching, jointly learning structured latent representations and high-fidelity generative models through a single objective.

Read the summary → OpenReview ↗ Yidan Xu +2

Connect your agent JSON API & MCP · no key, no rate limit

1 Claude Code / Cursor MCP · ~1 min

git clone https://github.com/dion-jy/spotlight-todai
pip install -r spotlight-todai/mcp/requirements.txt
claude mcp add spotlight-todai -- python spotlight-todai/mcp/server.py

Then ask: “what’s today’s spotlight paper?” Claude Desktop uses a JSON config instead — see mcp/README.

2 Shell / script nothing to install

curl -s https://dion-jy.github.io/spotlight-todai/api/daily.json | jq -r .paper.title

Plain HTTP GET on static files. Works from any language, and the same URLs open in a browser.

3 Any other agent zero setup

https://dion-jy.github.io/spotlight-todai/llms.txt

Paste that URL into ChatGPT, Perplexity or your own agent — it describes every endpoint so the model discovers the rest itself.

Endpoints: papers.json · daily.json · topics.json · venues.json · full API docs

#	Title	Author	Affiliation	Venue
1	Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training ↗	Pierre-Carl Langlais et al.	Pleias	ICLROral2026
2	Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training ↗	Artyom Sorokin et al.	Applied AI Institute	ICLROral2026
3	From movement to cognitive maps: recurrent neural networks reveal how locomotor development shapes hippocampal spatial coding ↗	Marco P Abrate et al.	University College London, University of London	ICLROral2026
4	FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff ↗	Isaac Han et al.	Gwangju Institute of Science and Technology	ICLROral2026
5	Exchangeability of GNN Representations with Applications to Graph Retrieval ↗	Kartik Nair et al.	Carnegie Mellon University	ICLROral2026
6	Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search ↗	Zhiyu Mou et al.	Alibaba Group	ICLROral2026
7	Why DPO is a Misspecified Estimator and How to Fix It ↗	Aditya Gopalan et al.	Indian Institute of Science	ICLROral2026
8	WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality ↗	Chunyang Li et al.	Department of Computer Science and Engineering, Hong Kong University of Science and Technology	ICLROral2026
9	SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety ↗	Geon-Hyeong Kim et al.	LG AI Research	ICLROral2026
10	MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science ↗	Ran Xu et al.	Google DeepMind	ICLROral2026
11	Optimistic Task Inference for Behavior Foundation Models ↗	Thomas Rupf et al.	ETHZ - ETH Zurich	ICLROral2026
12	CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering ↗	Yahan Li et al.		ICLROral2026
13	AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite ↗	Jonathan Bragg et al.	Allen Institute for Artificial Intelligence	ICLROral2026
14	Neon: Negative Extrapolation From Self-Training Improves Image Generation ↗	Sina Alemohammad et al.	University of Texas at Austin	ICLROral2026
15	Compositional Diffusion with Guided search for Long-Horizon Planning ↗	Utkarsh Aashu Mishra et al.	Georgia Institute of Technology	ICLROral2026
16	Visual symbolic mechanisms: Emergent symbol processing in Vision Language Models ↗	Rim Assouel et al.		ICLROral2026
17	Addressing divergent representations from causal interventions on neural networks ↗	Satchel Grant et al.	MATS	ICLROral2026
18	Cross-Domain Lossy Compression via Rate- and Classification-Constrained Optimal Transport ↗	Nam Nguyen et al.	Oregon State University	ICLROral2026
19	Latent Fourier Transform ↗	Mason Long Wang et al.	Massachusetts Institute of Technology	ICLROral2026
20	GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion Models ↗	Peter Holderrieth et al.	MIT	ICLROral2026
21	Latent Speech-Text Transformer ↗	Yen-Ju Lu et al.	Johns Hopkins University	ICLROral2026
22	LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts ↗	Siyuan Wang et al.	Shanghai Jiaotong University	ICLROral2026
23	Speculative Actions: A Lossless Framework for Faster AI Agents ↗	Naimeng Ye et al.	Columbia University	ICLROral2026
24	Gaussian certified unlearning in high dimensions: A hypothesis testing approach ↗	Aaradhya Pandey et al.	Princeton University	ICLROral2026
25	RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments ↗	Zeyi Liao et al.	Ohio State University, Columbus	ICLROral2026
26	Exploratory Causal Inference in SAEnce ↗	Tommaso Mencattini et al.	EPFL - EPF Lausanne	ICLROral2026
27	Every Language Model Has a Forgery-Resistant Signature ↗	Matthew Finlayson et al.	University of Southern California	ICLROral2026
28	Pre-training under infinite compute ↗	Konwoo Kim et al.		ICLROral2026
29	GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning ↗	Lakshya A Agrawal et al.	University of California, Berkeley	ICLROral2026
30	p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding ↗	Runyan Tan et al.	AI Labs, Thoughtworks	ICLROral2026
31	EigenBench: A Comparative Behavioral Measure of Value Alignment ↗	Jonathn Chang et al.	Cornell University	ICLROral2026
32	A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization ↗	Hideaki Kim et al. Hideaki Kim, Tomoharu Iwata	NTT	ICLROral2026
33	UALM: Unified Audio Language Model for Understanding, Generation and Reasoning ↗	Jinchuan Tian et al.	CMU, Carnegie Mellon University	ICLROral2026
34	Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents ↗	Yueqi Song et al.	Carnegie Mellon University	ICLROral2026
35	OpenApps: Simulating Environment Variations to Measure UI Agent Reliability ↗	Karen Ullrich et al.	Meta AI	ICLROral2026
36	Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks ↗	Brandon Livio Annesi et al.	University of Roma "La Sapienza"	ICLROral2026
37	Softmax Transformers are Turing-Complete ↗	Hongjian Jiang et al.	Rheinland-Pfälzische Technische Universität	ICLROral2026
38	Steering the Herd: A Framework for LLM-based Control of Social Learning ↗	Raghu Arghal et al.	University of Pennsylvania, University of Pennsylvania	ICLROral2026
39	Quantitative Bounds for Length Generalization in Transformers ↗	Zachary Izzo et al.	NEC Labs America	ICLROral2026
40	AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL ↗	Zhiheng Xi et al.	Fudan University	ICLROral2026
41	LLM Fingerprinting via Semantically Conditioned Watermarks ↗	Thibaud Gloaguen et al.	ETH Zurich	ICLROral2026
42	Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning ↗	Thibaud Gloaguen et al.	ETH Zurich	ICLROral2026
43	Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs) ↗	Nikita Maksimovich Kornilov et al.	Applied AI Institute	ICLROral2026
44	Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource ↗	Houyi Li et al.	Fudan University	ICLROral2026
45	Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization ↗	Jatan Shrestha et al.	Aalto University	ICLROral2026
46	The Coverage Principle: How Pre-Training Enables Post-Training ↗	Fan Chen et al.	Massachusetts Institute of Technology	ICLROral2026
47	Transformers are Inherently Succinct ↗	Pascal Bergsträßer et al.	Universität Kaiserslautern	ICLROral2026
48	Conformal Robustness Control: A New Strategy for Robust Decision ↗	Yang Hu et al.	Shanghai Jiaotong University	ICLROral2026
49	HATSolver: Learning Gröbner Bases with Hierarchical Attention Transformers ↗	Mohamed Malhou et al.		ICLROral2026
50	It's All Just Vectorization: einx, a Universal Notation for Tensor Operations ↗	Florian Fervers et al.	Fraunhofer IOSB	ICLROral2026
51	Fast training of accurate physics-informed neural networks without gradient descent ↗	Chinmay Datar et al.	Technische Universität München	ICLROral2026
52	In-Place Test-Time Training ↗	Guhao Feng et al.	Peking University	ICLROral2026
53	RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format ↗	Zhehao Huang et al.	Shanghai Jiaotong University	ICLROral2026
54	To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models ↗	Eran Malach et al.	Apple	ICLROral2026
55	TileLang: Bridge Programmability and Performance in Modern Neural Kernels ↗	Lei Wang et al.	Peking University	ICLROral2026
56	Navigating the Latent Space Dynamics of Neural Models ↗	Marco Fumero et al.		ICLROral2026
57	Non-Asymptotic Analysis of (Sticky) Track-and-Stop ↗	Riccardo Poiani et al.	Bocconi University	ICLROral2026
58	The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology ↗	Aideen Fay et al.	Imperial College London	ICLROral2026
59	Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport ↗	Harry Amad et al.	University of Cambridge	ICLROral2026
60	Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction–Reasoning Synergy ↗	Haijier Chen et al.	Wuhan University	ICLROral2026
61	From Markov to Laplace: How Mamba In-Context Learns Markov Chains ↗	Marco Bondaschi et al.	EPFL - EPF Lausanne	ICLROral2026
62	Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine ↗	Wenyi Wang et al.	King Abdullah University of Science and Technology	ICLROral2026
63	Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments ↗	Romain Froger et al.	Facebook	ICLROral2026
64	Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data ↗	Guillaume Braun et al.	RIKEN	ICLROral2026
65	AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms ↗	Zhenxing Xu et al.	National University of Defense Technology	ICLROral2026
66	On the Wasserstein Geodesic Principal Component Analysis of probability measures ↗	Nina Vesseron et al.	Ecole Nationale de la Statistique et de l'Administration Economique	ICLROral2026
67	Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces ↗	Bryon Tjanaka et al.	University of Southern California	ICLROral2026
68	Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series ↗	Guoqi Yu et al.		ICLROral2026
69	Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention ↗	Haiquan Qiu et al. Haiquan Qiu, Quanming Yao	Tsinghua University, Tsinghua University	ICLROral2026
70	Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding ↗	Yuxuan Zhou et al.	Baidu	ICLROral2026
71	In-the-Flow Agentic System Optimization for Effective Planning and Tool Use ↗	Zhuofeng Li et al.	Texas A&M University - College Station	ICLROral2026
72	What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data ↗	Rajiv Movva et al.	University of California, Berkeley	ICLROral2026
73	SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents ↗	Gyuhyeon Seo et al.	Seoul National University	ICLROral2026
74	Reasoning with Sampling: Your Base Model is Smarter Than You Think ↗	Aayush Karan et al. Aayush Karan, Yilun Du	Harvard University	ICLROral2026
75	Learning to Segment for Vehicle Routing Problems ↗	Wenbin Ouyang et al.	Massachusetts Institute of Technology	ICLROral2026
76	WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM ↗	Changli Tang et al.	Tsinghua University, Tsinghua University	ICLROral2026
77	mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules ↗	Carl Edwards et al.	Genentech	ICLROral2026
78	Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI ↗	Zheng Huang et al.		ICLROral2026
79	Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability ↗	Usha Bhalla et al.		ICLROral2026
80	VibeVoice: Expressive Podcast Generation with Next-Token Diffusion ↗	Zhiliang Peng et al.	Microsoft	ICLROral2026
81	AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference ↗	Jing Yao et al.	Microsoft	ICLROral2026
82	Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences ↗	Zhuoran Jin et al.	Institute of Automation, Chinese Academy of Sciences	ICLROral2026
83	Spherical Watermark: Encryption-Free, Lossless Watermarking for Diffusion Models ↗	Xiaoxiao Hu et al.	Fudan University	ICLROral2026
84	Rodrigues Network for Learning Robot Actions ↗	Jialiang Zhang et al.	Peking University	ICLROral2026
85	CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale ↗	Zhun Wang et al.		ICLROral2026
86	Energy-Based Transformers are Scalable Learners and Thinkers ↗	Alexi Gladstone et al.	Flapping Airplanes	ICLROral2026
87	Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Optimization ↗	Rahul Krishna Thomas et al. Rahul Krishna Thomas, Arka Pal	Columbia University	ICLROral2026
88	FALCON: Few-step Accurate Likelihoods for Continuous Flows ↗	Danyal Rehman et al.	Mila - Quebec Artificial Intelligence Institute	ICLROral2026
89	How Reliable is Language Model Micro-Benchmarking? ↗	Gregory Yauney et al.	Amazon	ICLROral2026
90	EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits ↗	Wayne Chi et al.	Carnegie Mellon University	ICLROral2026
91	Online Learning and Equilibrium Computation with Ranking Feedback ↗	Mingyang Liu et al.	Massachusetts Institute of Technology	ICLROral2026
92	MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains ↗	Xuying Ning et al.	University of Illinois at Urbana-Champaign	ICLROral2026
93	True Self-Supervised Novel View Synthesis is Transferable ↗	Thomas Mitchel et al.		ICLROral2026
94	Revela: Dense Retriever Learning via Language Modeling ↗	Fengyu Cai et al.	Technische Universität Darmstadt	ICLROral2026
95	LLMs Get Lost In Multi-Turn Conversation ↗	Philippe Laban et al.	Microsoft	ICLROral2026
96	TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems ↗	Christoph Minixhofer et al.	University of Edinburgh, University of Edinburgh	ICLROral2026
97	Mamba-3: Improved Sequence Modeling using State Space Principles ↗	Aakash Lahoti et al.	CMU, Carnegie Mellon University	ICLROral2026
98	Is it Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort ↗	Xinpeng Wang et al.	Ludwig-Maximilians-Universität München	ICLROral2026
99	Causal Structure Learning in Hawkes Processes with Complex Latent Confounder Networks ↗	Songyao Jin et al. Songyao Jin, Biwei Huang	University of California, San Diego	ICLROral2026
100	Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation ↗	Guojian Zhan et al.	Tsinghua University	ICLROral2026
101	Radiometrically Consistent Gaussian Surfels for Inverse Rendering ↗	Kyu Beom Han et al.	Korea Advanced Institute of Science & Technology	ICLROral2026
102	Hubble: a Model Suite to Advance the Study of LLM Memorization ↗	Johnny Wei et al.	University of Southern California	ICLROral2026
103	Differentially Private Domain Discovery ↗	Vinod Raman et al.	Google DeepMind	ICLROral2026
104	CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data ↗	Shifeng Xie et al.	Télécom Paris	ICLROral2026
105	Non-Convex Federated Optimization under Cost-Aware Client Selection ↗	Xiaowen Jiang et al.	CISPA Helmholtz Center for Information Security	ICLROral2026
106	Verifying Chain-of-Thought Reasoning via Its Computational Graph ↗	Zheng Zhao et al.	University of Edinburgh, University of Edinburgh	ICLROral2026
107	How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining ↗	Kairong Luo et al.	Tsinghua University	ICLROral2026
108	Probabilistic Kernel Function for Fast Angle Testing ↗	Kejing Lu et al.	Yamanashi University	ICLROral2026
109	RefineStat: Efficient Exploration for Probabilistic Program Synthesis ↗	Madhav Kanda et al.	University of Illinois at Urbana-Champaign	ICLROral2026
110	Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute ↗	Kieran Didi et al.	NVIDIA	ICLROral2026
111	Structured Flow Autoencoders: Learning Structured Probabilistic Representations with Flow Matching ↗	Yidan Xu et al.		ICLROral2026
112	Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models ↗	Weiduo Liao et al.	City University of Hong Kong	ICLROral2026
113	Generating metamers of human scene understanding ↗	Ritik Raina et al.	State University of New York at Stony Brook	ICLROral2026
114	Efficient Resource-Constrained Training of Transformers via Subspace Optimization ↗	Le-Trung Nguyen et al.	Télécom Paris	ICLROral2026
115	Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment ↗	Haobin Li et al.	School of Software Engineering, Sichuan University, Sichuan University	ICLROral2026
116	Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers ↗	Panagiotis D. Grontas et al.	International Business Machines	ICLROral2026
117	ParaRNN: Unlocking Parallel Training of Nonlinear RNNs for Large Language Models ↗	Federico Danieli et al.	Apple	ICLROral2026
118	Exploring Synthesizable Chemical Space with Iterative Pathway Refinements ↗	Seul Lee et al.	Korea Advanced Institute of Science and Technology	ICLROral2026
119	On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning ↗	Tongtian Zhu et al.	Zhejiang University	ICLROral2026
120	Visual Planning: Let's Think Only with Images ↗	Yi Xu et al.	Mistral AI	ICLROral2026
121	Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks ↗	Taishi Nakamura et al.	Institute of Science Tokyo	ICLROral2026
122	Exploratory Diffusion Model for Unsupervised Reinforcement Learning ↗	Chengyang Ying et al.	Tsinghua University, Tsinghua University	ICLROral2026
123	DCFold: Efficient Protein Structure Generation with Single Forward Pass ↗	Zhe Zhang et al.	Tsinghua University	ICLROral2026
124	Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms? ↗	Zijian Zhao et al. Zijian Zhao, Sen Li	Huawei Technologies Ltd.	ICLROral2026
125	InfoNCE Induces Gaussian Distribution ↗	Roy Betser et al.	Technion - Israel Institute of Technology, Technion	ICLROral2026
126	Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss ↗	Ang Lv et al.	Renmin University of China	ICLROral2026
127	P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling ↗	Pinyi Zhang et al.	East China Normal University	ICLROral2026
128	Modality-free Graph In-context Alignment ↗	Wei Zhuo et al. Wei Zhuo, Siqiang Luo	Nanyang Technological University	ICLROral2026
129	TRACE: Your Diffusion Model is Secretly an Instance Edge Detector ↗	Sanghyun Jo et al.	OGQ	ICLROral2026
130	Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime ↗	Leonardo Defilippis et al.	Ecole Normale Supérieure, Ecole Normale Supérieure de Paris	ICLROral2026
131	MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent ↗	Hongli Yu et al.	Tsinghua University	ICLROral2026
132	TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning ↗	Marco Bagatella et al.	Max Planck Institute for Intelligent Systems, Max Planck Institute for Intelligent Systems	ICLROral2026
133	NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale ↗	Chunrui Han et al.	Stepfun	ICLROral2026
134	Differentiable Model Predictive Control on the GPU ↗	Emre Adabag et al.	University of Michigan - Ann Arbor	ICLROral2026
135	Planner Aware Path Learning in Diffusion Language Models Training ↗	Fred Zhangzhi Peng et al.	Duke University	ICLROral2026
136	PateGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning ↗	Yingjie Ma et al.		ICLROral2026
137	MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction ↗	Zilin Xiao et al.	Rice University	ICLROral2026
138	Monocular Normal Estimation via Shading Sequence Estimation ↗	Zongrui Li et al.	Nanyang Technological University	ICLROral2026
139	Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People ↗	Gabriel Grand et al.	Massachusetts Institute of Technology	ICLROral2026
140	Intrinsic Entropy of Context Length Scaling in LLMs ↗	Jingzhe Shi et al.	Tsinghua University	ICLROral2026
141	Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling ↗	Tal Daniel et al.	Carnegie Mellon University	ICLROral2026
142	Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts ↗	Zhaomin Wu et al.	National University of Singapore	ICLROral2026
143	LLM DNA: Tracing Model Evolution via Functional Representations ↗	Zhaomin Wu et al.	National University of Singapore	ICLROral2026
144	Generative Universal Verifier as Multimodal Meta-Reasoner ↗	Xinchen Zhang et al.	ByteDance Seed	ICLROral2026
145	$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models ↗	Jing Gu et al.	xAI	ICLROral2026
146	World-In-World: World Models in a Closed-Loop World ↗	Jiahan Zhang et al.		ICLROral2026
147	Multimodal Aligned Semantic Knowledge for Unpaired Image-text Matching ↗	Laiguo Yin et al.	Shandong University	ICLROral2026
148	DiffusionNFT: Online Diffusion Reinforcement with Forward Process ↗	Kaiwen Zheng et al.	Tsinghua University	ICLROral2026
149	The Spacetime of Diffusion Models: An Information Geometry Perspective ↗	Rafal Karczewski et al.	Aalto University	ICLROral2026
150	Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents ↗	Deyu Zou et al.	Department of Computer Science and Engineering, The Chinese University of Hong Kong	ICLROral2026
151	Information Shapes Koopman Representation ↗	Xiaoyuan Cheng et al.	University College London, University of London	ICLROral2026
152	Sequences of Logits Reveal the Low Rank Structure of Language Models ↗	Noah Golowich et al.	Microsoft	ICLROral2026
153	BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions ↗	Nan Huo et al.	the University of Hong Kong, University of Hong Kong	ICLROral2026
154	EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning ↗	Xuan Ju et al.	Chinese University of Hong Kong	ICLROral2026
155	The Art of Scaling Reinforcement Learning Compute for LLMs ↗	Fnu Devvrit et al.	, University of Texas at Austin	ICLROral2026
156	Partition Generative Modeling: Masked Modeling Without Masks ↗	Justin Deschenaux et al.	EPFL - EPF Lausanne	ICLROral2026
157	How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability ↗	Shawn Im et al.	Department of Computer Science, University of Wisconsin - Madison	ICLROral2026
158	On the Reasoning Abilities of Masked Diffusion Language Models ↗	Anej Svete et al. Anej Svete, Ashish Sabharwal	Department of Computer Science, ETHZ - ETH Zurich	ICLROral2026
159	FRABench and UFEval: Unified Fine-grained Evaluation with Task and Aspect Generalization ↗	Shibo Hong et al.	Fudan University	ICLROral2026
160	Quotient-Space Diffusion Models ↗	Yixian Xu et al.	Peking University	ICLROral2026
161	SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving ↗	Wendong XU et al.	University of Hong Kong	ICLROral2026
162	AnyUp: Universal Feature Upsampling ↗	Thomas Wimmer et al.	Max-Planck Institute	ICLROral2026
163	High-dimensional Analysis of Synthetic Data Selection ↗	Parham Rezaei et al.	Institute of Science and Technology Austria	ICLROral2026
164	Task-free Adaptive Meta Black-box Optimization ↗	Chao Wang et al.	Xidian University	ICLROral2026
165	Token-Importance Guided Direct Preference Optimization ↗	Ning Yang et al.	Institute of automation, Chinese academy of science, Chinese Academy of Sciences	ICLROral2026
166	DTO-KD: Dynamic Trade-off Optimization for Effective Knowledge Distillation ↗	Zeeshan Hayder et al.	Google	ICLROral2026
167	Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning ↗	Haoyue Dai et al.	Carnegie Mellon University	ICLROral2026
168	Reliable Weak-to-Strong Monitoring of LLM Agents ↗	Neil Kale et al.	School of Computer Science, Carnegie Mellon University	ICLROral2026
169	Multiplayer Nash Preference Optimization ↗	Fang Wu et al.		ICLROral2026
170	Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models ↗	Li Sun et al.	Beijing University of Post and Telecommunications	ICLROral2026
171	TROLL: Trust Regions Improve Reinforcement Learning for Large Language Models ↗	Philipp Becker et al.	Facebook	ICLROral2026
172	FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging ↗	Ziyang Fan et al.	Harbin Institute of Technology, Shenzhen	ICLROral2026
173	WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training ↗	Changxin Tian et al.	Ant Group	ICLROral2026
174	MrRoPE: Mixed-radix Rotary Position Embedding ↗	Qingyuan Tian et al.	Shanghai Jiaotong University	ICLROral2026
175	OpenThoughts: Data Recipes for Reasoning Models ↗	Etash Kumar Guha et al.	RIKEN	ICLROral2026
176	Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator ↗	Hyojun Go et al.	ETHZ - ETH Zurich	ICLROral2026
177	A Scalable Distributed Framework for Multimodal GigaVoxel Image Registration ↗	Rohit Jena et al.	University of Pennsylvania	ICLROral2026
178	Invisible Safety Threat: Malicious Finetuning for LLM via Steganography ↗	Guangnian Wan et al.	National University of Singapore	ICLROral2026
179	Temporal superposition and feature geometry of RNNs under memory demands ↗	Pratyaksh Sharma et al.	G-Research	ICLROral2026
180	InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression ↗	Haotian Ye et al.	Stanford University	ICLROral2026
181	Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference ↗	Ben Finkelshtein et al.	University of Oxford	ICLROral2026
182	Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs ↗	Zhiyu Pan et al.	Alibaba Group	ICLROral2026
183	SAFETY-GUIDED FLOW (SGF): A UNIFIED FRAMEWORK FOR NEGATIVE GUIDANCE IN SAFE GENERATION ↗	Mingyu Kim et al.	Kookmin University	ICLROral2026
184	Depth Anything 3: Recovering the Visual Space from Any Views ↗	Haotong Lin et al.	Zhejiang University	ICLROral2026
185	Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation ↗	Zhengbo Wang et al.	University of Science and Technology of China	ICLROral2026
186	Premise Selection for a Lean Hammer ↗	Thomas Zhu et al.	ByteDance Inc.	ICLROral2026
187	DepthLM: Metric Depth from Vision Language Models ↗	Zhipeng Cai et al.	Meta	ICLROral2026
188	Hallucination Begins Where Saliency Drops ↗	Xiaofeng Zhang et al.	Shanghai Jiao Tong University	ICLROral2026
189	Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling ↗	Shuyang Jiang et al.	Fudan University	ICLROral2026
190	On the Generalization Capacities of MLLMs for Spatial Intelligence ↗	Gongjie Zhang et al.	Alibaba Group	ICLROral2026
191	The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm ↗	Noah Amsel et al.	NYU, New York University	ICLROral2026
192	Characterizing the Discrete Geometry of ReLU Networks ↗	Blake B. Gaines et al. Blake B. Gaines, Jinbo Bi	University of Connecticut	ICLROral2026
193	ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models ↗	Akshat Ramachandran et al.	Georgia Institute of Technology	ICLROral2026
194	Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective ↗	Yi-Ge Zhang et al.	Peking University	ICLROral2026
195	Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers ↗	Shikang Zheng et al.		ICLROral2026
196	MotionStream: Real-Time Video Generation with Interactive Motion Controls ↗	Joonghyuk Shin et al.	Seoul National University	ICLROral2026
197	BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignals ↗	Chenqi Li et al.	University of Oxford	ICLROral2026
198	Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering ↗	Wei Ju et al.		ICLROral2026
199	WAFT: Warping-Alone Field Transforms for Optical Flow ↗	Yihan Wang et al. Yihan Wang, Jia Deng	Princeton University	ICLROral2026
200	FlashWorld: High-quality 3D Scene Generation within Seconds ↗	Xinyang Li et al.	Xiamen University	ICLROral2026
201	TabStruct: Measuring Structural Fidelity of Tabular Data ↗	Xiangjian Jiang et al.	University of Cambridge	ICLROral2026
202	Uncover Underlying Correspondence for Robust Multi-view Clustering ↗	Haochen Zhou et al.	Sichuan University	ICLROral2026
203	Instilling an Active Mind in Avatars via Cognitive Simulation ↗	Jianwen Jiang et al.		ICLROral2026
204	Diffusion Language Model Knows the Answer Before It Decodes ↗	Pengxiang Li et al.	Hong Kong Polytechnic University	ICLROral2026
205	Generative Human Geometry Distribution ↗	Xiangjun Tang et al.	King Abdullah University of Science and Technology	ICLROral2026
206	EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning ↗	Dingdong WANG et al.	Chinese University of Hong Kong, The Chinese University of Hong Kong	ICLROral2026
207	Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning ↗	Yaoyu Wang et al.	University of Chinese Academy of Sciences	ICLROral2026
208	LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning ↗	Yuhao Wu et al.	Singapore University of Technology and Design	ICLROral2026
209	RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data ↗	Peiyan Hu et al.	Chinese Academy of Sciences	ICLROral2026
210	Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation ↗	Feng Hong et al.	Shanghai Jiao Tong University	ICLROral2026
211	SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer ↗	Junsong Chen et al.	University of Hong Kong	ICLROral2026
212	Stable Video Infinity: Infinite-Length Video Generation with Error Recycling ↗	Wuyang Li et al.	EPFL - EPF Lausanne	ICLROral2026
213	Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction ↗	Zhao Yang et al.	Renmin University of China	ICLROral2026
214	MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning ↗	Yuanchen Ju et al.		ICLROral2026
215	Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training ↗	Junlin Han et al.	University of Oxford	ICLROral2026
216	Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models ↗	Bartłomiej Marek et al.	CISPA Helmholtz Center for Information Security	ICLROral2026
217	ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data ↗	Zhaoyang Liu et al.	Hong Kong University of Science and Technology	ICLROral2026
218	Train-before-Test Harmonizes Language Model Rankings ↗	Guanhua Zhang et al.	Max Planck Institute for Intelligent Systems, Max-Planck Institute	ICLROral2026
219	One for Two: A Unified Framework for Imbalanced Graph Classification via Dynamic Balanced Prototype ↗	Guanjun Wang et al.	University of Science and Technology of China	ICLROral2026
220	Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning ↗	Hao Tan et al.	Institute of automation, Chinese Academy of Sciences	ICLROral2026
221	Semi-Supervised Preference Optimization with Limited Feedback ↗	Seonggyun Lee et al.	Yonsei University	ICLROral2026
222	Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation ↗	Zhuoyang Zhang et al.	Massachusetts Institute of Technology	ICLROral2026
223	Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment ↗	Shijie Zhao et al.	ByteDance Inc.	ICLROral2026
224	Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer ↗	Tao Ren et al.	Peking University	ICLROral2026
1	Benchmarking at the Edge of Comprehension ↗	Samuele Marro et al.		ICMLOral2026
2	Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization ↗	Kenshi Abe et al.		ICMLOral2026
3	Position: Don't Just "Fix it in Post'': A Science of AI Must Study Learning Dynamics ↗	Stella Biderman et al.		ICMLOral2026
4	dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning ↗	Arnav Shah et al.		ICMLOral2026
5	Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination ↗	Chufan Shi et al.		ICMLOral2026
6	Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs ↗	Sagnik Mukherjee et al.		ICMLOral2026
7	DiScoFormer: Plug-In Density and Score Estimation with Transformers ↗	Vasily Ilin et al.		ICMLOral2026
8	CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Subtitle Removal ↗	Qingdong He et al.		ICMLOral2026
9	A Systematic Study of Behavioral Cloning for Scientific Data Annotation ↗	Ishaan Singh Chandok et al.		ICMLOral2026
10	Mixtures Closest To A Given Measure: A Semidefinite Programming Approach ↗	Srećko Ðurašinović et al.		ICMLOral2026
11	FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications ↗	Kieran Didi et al.		ICMLOral2026
12	daVinci-Dev: Agent-native Mid-training for Software Engineering ↗	Ji Zeng et al.		ICMLOral2026
13	Learning Unmasking Policies for Diffusion Language Models ↗	Metod Jazbec et al.		ICMLOral2026
14	LASER: Learning Active Sensing for Continuum Field Reconstruction ↗	Huayu Deng et al.		ICMLOral2026
15	Protein Autoregressive Modeling via Multiscale Structure Generation ↗	Yanru Qu et al.		ICMLOral2026
16	Multimodal Nested Learning for Decoupled and Coordinated Optimization ↗	Yanglin Feng et al.		ICMLOral2026
17	AI Engram: In Search of Memory Traces in Artificial Intelligence ↗	Jea Kwon et al.		ICMLOral2026
18	On the Convergence Rate of LoRA Gradient Descent ↗	Siqiao Mu et al. Siqiao Mu, Diego Klabjan		ICMLOral2026
19	Motion Attribution for Video Generation ↗	Xindi Wu et al.		ICMLOral2026
20	Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs ↗	Zhongzhi Li et al.		ICMLOral2026
21	Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections ↗	Lukasz Borchmann et al.		ICMLOral2026
22	Protein Fold Classification at Scale: Benchmarking and Pretraining ↗	Dexiong Chen et al.		ICMLOral2026
23	VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics ↗	Yichen Gong et al.		ICMLOral2026
24	OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration ↗	Shaobo Wang et al.		ICMLOral2026
25	Guaranteed Optimal Compositional Explanations for Neurons ↗	Biagio La Rosa et al. Biagio La Rosa, Leilani Gilpin		ICMLOral2026
26	Revenue Efficiency of Correlated Equilibria in First Price Auctions ↗	Anders Bo Ipsen et al.		ICMLOral2026
27	Riemannian Metric Matching for Scalable Geometric Modeling of Distributions ↗	Jacob Bamberger et al.		ICMLOral2026
28	PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models ↗	Mingde Yao et al.		ICMLOral2026
29	Position: Anthropomorphic Misalignment Research Needs Stronger Evidence ↗	Vansh Gupta et al.		ICMLOral2026
30	Diffract: Spectral View of LLM Domain Adaptation ↗	Nikita Borodin et al.		ICMLOral2026
31	Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization ↗	Hao Zhang et al.		ICMLOral2026
32	From Feasible to Practical: Pareto-Optimal Synthesis Planning ↗	Friedrich Hastedt et al.		ICMLOral2026
33	Controlled LLM Training on Spectral Sphere ↗	Tian Xie et al.		ICMLOral2026
34	Don't Force the Fit: Bounded Log-Likelihood Loss for Enhanced Reasoning in Large Language Models ↗	Feng Zhao et al.		ICMLOral2026
35	Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-dimensional Control Tasks ↗	Stefan Huber et al.		ICMLOral2026
36	Monitoring Monitorability ↗	Melody Guan et al.		ICMLOral2026
37	Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges ↗	Usman A Khan et al. Usman A Khan, Joseph Durham		ICMLOral2026
38	ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers ↗	Hao Wei et al.		ICMLOral2026
39	Evaluating Robustness of Reasoning Models on Parameterized Logical Problems ↗	Naïm Es-sebbani et al.		ICMLOral2026
40	Detecting the Semantic Fixed Point: A Geometric Framework for Efficient Inference ↗	Jiawei Gu et al. Jiawei Gu, Ziyue Qiao, Xiao Luo		ICMLOral2026
41	Maximum Likelihood Reinforcement Learning ↗	Fahim Tajwar et al.		ICMLOral2026
42	Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks ↗	Yoshihiro Maruyama		ICMLOral2026
43	Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers ↗	Zander Blasingame et al. Zander Blasingame, Chen Liu		ICMLOral2026
44	ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios ↗	Xinyi Hu et al.		ICMLOral2026
45	The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes ↗	Mohammad Taufeeque et al.		ICMLOral2026
46	On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions ↗	Sejun Park et al.		ICMLOral2026
47	RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies ↗	Yinpei Dai et al.		ICMLOral2026
48	Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning ↗	Harin Lee et al. Harin Lee, Kevin Jamieson		ICMLOral2026
49	TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains ↗	Liang Su et al.		ICMLOral2026
50	The Expressivity Limits of Transformers ↗	Maxime Meyer et al.		ICMLOral2026
51	Optimal Decision-Making Based on Prediction Sets ↗	Tao Wang et al. Tao Wang, Edgar Dobriban		ICMLOral2026
52	Towards Sub-second Biological Foundation Model Infrastructure: A Quantized Consistency Diffusion Framework for Molecular Docking ↗	Kexin Zhang et al.		ICMLOral2026
53	Understanding Reasoning Collapse in LLM Agent Reinforcement Learning ↗	Zihan (Zenus) Wang et al.		ICMLOral2026
54	VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models ↗	Woojin Kim et al.		ICMLOral2026
55	Unsupervised Partner Design Enables Robust Ad-hoc Teamwork ↗	Constantin Ruhdorfer et al.		ICMLOral2026
56	MuonSSM: Orthogonalizing State Space Models for Sequence Modeling ↗	Thai Khanh Nguyen et al.		ICMLOral2026
57	Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling ↗	Zhibin Duan et al.		ICMLOral2026
58	Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture ↗	Shuchen Xue et al.		ICMLOral2026
59	Position: Irresponsible AI: big tech’s influence on AI research and associated impacts ↗	Alex Hernandez-Garcia et al.		ICMLOral2026
60	Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning ↗	WANG et al.		ICMLOral2026
61	Position: Stop Automating Peer Review Without Rigorous Evaluation ↗	Joachim Baumann et al.		ICMLOral2026
62	Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking ↗	Zhicheng Fang et al.		ICMLOral2026
63	Exact Functional ANOVA Decomposition for Categorical Inputs ↗	Baptiste Ferrere et al.		ICMLOral2026
64	Quantifying Frontier LLM Capabilities for Container Sandbox Escape ↗	Rahul Marchand et al.		ICMLOral2026
65	Joint Learning in the Gaussian Single Index Model ↗	Loucas Pillaud-Vivien et al.		ICMLOral2026
66	Position: The AI Imperative: Scaling High-Quality Peer Review in Machine Learning ↗	Qiyao Wei et al.		ICMLOral2026
67	DroneDINO: Towards Heterogeneous Routed Mixture of Experts for Drone-based Unified Object Detection ↗	Rui Chen et al.		ICMLOral2026
68	Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion Models ↗	Songwei Liu et al.		ICMLOral2026
69	Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers ↗	Adam Karvonen et al.		ICMLOral2026
70	Reinforcement Learning with Evolving Rubrics for Deep Research ↗	Rulin Shao et al.		ICMLOral2026
71	Simultaneous Speech-to-Speech Translation Without Aligned Data ↗	Tom Labiausse et al.		ICMLOral2026
72	Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning ↗	Rachael Hwee Ling Sim et al.		ICMLOral2026
73	SVRG and Beyond via Posterior Correction ↗	Nico Daheim et al.		ICMLOral2026
74	Lottery Prior: Randomized Neural Compression for Zero-Shot Inverse Problems ↗	Haotian Wu et al.		ICMLOral2026
75	Large Language Models Develop Novel Social Biases Through Adaptive Exploration ↗	Addison J. Wu et al.		ICMLOral2026
76	High-accuracy and dimension-free sampling with diffusions ↗	Khashayar Gatmiry et al.		ICMLOral2026
77	Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models ↗	Yanchen Yin et al.		ICMLOral2026
78	The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models ↗	Zanlin Ni et al.		ICMLOral2026
79	Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives ↗	Ander Artola Velasco et al.		ICMLOral2026
80	Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units ↗	Jianhui Chen et al.		ICMLOral2026
81	Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning ↗	Minh-Tung Luu et al.		ICMLOral2026
82	Scalable Event Cloud Network for Event-based Classification ↗	Hongwei Ren et al.		ICMLOral2026
83	Towards Fair Sequential Decision-Making: A Causal Decomposition Approach ↗	Jiajun Chen et al.		ICMLOral2026
84	When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models ↗	Jiacheng Hou et al.		ICMLOral2026
85	A Recursive Decomposition Framework for Causal Structure Learning in the Presence of Latent Variables ↗	Zheng Li et al.		ICMLOral2026
86	ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence ↗	Shiyu Wang et al.		ICMLOral2026
87	CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs ↗	Shigeng Wang et al.		ICMLOral2026
88	CoEvol-NO: State and Coordinate Co-Evolution with an Error-Driven Predictor-Corrector Paradigm for Neural Operator Transformer ↗	Jianqiao Zeng et al.		ICMLOral2026
89	DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable) ↗	Wenxuan Zhou et al.		ICMLOral2026
90	Position: The Alignment Community is Unintentionally Building a Censor’s Toolkit ↗	Sarah Ball et al. Sarah Ball, Phil Hackemann		ICMLOral2026
91	From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model ↗	Bing Hu et al.		ICMLOral2026
92	Information Flow Reveals When to Trust Language Models ↗	Rui Xu et al.		ICMLOral2026
93	From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space ↗	Lehui Li et al.		ICMLOral2026
94	High-accuracy sampling for diffusion models and log-concave distributions ↗	Fan Chen et al.		ICMLOral2026
95	From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models ↗	Yihan Lin et al.		ICMLOral2026
96	POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation ↗	Zeju Qiu et al.		ICMLOral2026
97	DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation ↗	Emre Kavak et al.		ICMLOral2026
98	Geometric Flow Grounding: A Unified Manifold Decoupling Framework for Dynamics Discovery and Verification ↗	Chang Yu et al.		ICMLOral2026
99	Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning ↗	Huihan Liu et al.		ICMLOral2026
100	Solving Time-Dependent Differential Equations with Physical Dynamical Systems ↗	Chuan Liu et al.		ICMLOral2026
101	Modeling Hierarchical Thinking in Large Reasoning Models ↗	G M Shahariar et al.		ICMLOral2026
102	Rational Transductors ↗	Mehryar Mohri		ICMLOral2026
103	Markov Chain Monte Carlo without Evaluating the Target: an Auxiliary Variable Approach ↗	Wei Yuan et al. Wei Yuan, Guanyang Wang		ICMLOral2026
104	Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference ↗	Shengxian Ding et al.		ICMLOral2026
105	ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training ↗	Janghwan Lee et al.		ICMLOral2026
106	Path-dependent Discrete Amortized Inference ↗	Tiago Silva et al.		ICMLOral2026
107	To Grok Grokking: Provable Grokking in Ridge Regression ↗	Mingyue Xu et al.		ICMLOral2026
108	Training-Free Bayesian Filtering with Generative Emulators ↗	Thomas Savary et al.		ICMLOral2026
109	XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations ↗	Shichao Fan et al.		ICMLOral2026
110	Skip a Layer or Loop It? Learning Program-of-Layers in LLMs ↗	Ziyue Li et al. Ziyue Li, Yang Li, Tianyi Zhou		ICMLOral2026
111	On the Identifiability of Poisson Branching Structural Causal Model Under Latent Confounding ↗	Jie Qiao et al.		ICMLOral2026
112	Reward-free Alignment for Conflicting Objectives ↗	Peter Chen et al.		ICMLOral2026
113	Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust? ↗	Muquan Li et al.		ICMLOral2026
114	Position: There are futures that benchmark-driven AI cannot see ↗	Sobhan Lotfi et al.		ICMLOral2026
115	FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space ↗	Jiahong Liu et al.		ICMLOral2026
116	Necessary Conditions for Compositional Generalization of Embedding Models ↗	Arnas Uselis et al.		ICMLOral2026
117	3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models ↗	Shaoxiong Zhan et al.		ICMLOral2026
118	Midtraining Bridges Pretraining and Posttraining Distributions ↗	Emmy Liu et al.		ICMLOral2026
119	Distributional Inverse Reinforcement Learning ↗	Feiyang Wu et al. Feiyang Wu, Ye Zhao, Anqi Wu		ICMLOral2026
120	ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models ↗	Long (Tony) Lian et al.		ICMLOral2026
121	On the Difficulty of Learning a Meta-network for Training Data Selection ↗	Zilin Du et al.		ICMLOral2026
122	On Computation and Reinforcement Learning ↗	Raj Ghugare et al.		ICMLOral2026
123	Non-Euclidean Gradient Descent Operates at the Edge of Stability ↗	Rustem Islamov et al.		ICMLOral2026
124	CausalGame: Benchmarking Causal Thinking of LLM Agents in Games ↗	Zhenhao Chen et al.		ICMLOral2026
125	MV-FGAD: Towards Efficient and Effective Federated Graph Anomaly Detection via Multi-view Learning ↗	Junyi Yan et al.		ICMLOral2026
126	Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning ↗	Jiaqi Liu et al.		ICMLOral2026
127	PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA ↗	Shihao Wang et al. Shihao Wang, Xueru Zhang		ICMLOral2026
128	TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior ↗	Gül Sena Altıntaş et al.		ICMLOral2026
129	The Signal is in the Steps: Local Scoring for Reasoning Data Selection ↗	Hoang Anh Just et al.		ICMLOral2026
130	Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing ↗	Tuan Dam		ICMLOral2026
131	Characterizing, Evaluating, and Optimizing Complex Reasoning ↗	Haoran Zhang et al.		ICMLOral2026
132	PhenoBrain: Phenotype-Conditioned Long-Range Communication for Multi-Modal Brain Network Analysis ↗	Lingyuan Meng et al.		ICMLOral2026
133	Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence ↗	Yuanyuan Gao et al.		ICMLOral2026
134	Robust Contextual Optimization with Missing Covariates ↗	Qingyuan Xu et al. Qingyuan Xu, Ruiwei Jiang		ICMLOral2026
135	Towards Hierarchy–Uniformity Equilibrium: Recovering Semantic Depth in Hypergraph Contrastive Learning ↗	Ruiting Zhao et al.		ICMLOral2026
136	Transforming Weather Data from Pixel to Latent Space ↗	Sijie Zhao et al.		ICMLOral2026
137	SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models ↗	jing wu et al.		ICMLOral2026
138	Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods ↗	Jeong Woon Lee et al.		ICMLOral2026
139	Rare Event Analysis of Large Language Models ↗	Jake McAllister Dorman et al.		ICMLOral2026
140	WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference ↗	Aiwei Liu et al.		ICMLOral2026
141	A Random Matrix Perspective on the Consistency of Diffusion Models ↗	Binxu Wang et al.		ICMLOral2026
142	Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models ↗	John Cooper et al.		ICMLOral2026
143	$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment ↗	Victor Barres et al.		ICMLOral2026
144	DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs ↗	Kaiqi Chen et al.		ICMLOral2026
145	Faster Activation Functions at the Edge for Post-Training Speedups ↗	Anton Lydike et al.		ICMLOral2026
146	Position: AI Should Facilitate Democratic Deliberation at Scale ↗	José Ramón Enríquez et al.		ICMLOral2026
147	Position: AI/ML Deepfake Research is Misaligned with AI Generated Non-Consensual Intimate Imagery (AIG-NCII) ↗	Qiwei Li et al.		ICMLOral2026
148	Equilibrium Pricing in Oligopolistic Data Markets ↗	Bhaskar Ray Chaudhury et al.		ICMLOral2026
149	FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU ↗	Felix X.-F. Ye et al.		ICMLOral2026
150	Characterizing Agents in Production ↗	Melissa Pan et al.		ICMLOral2026
151	Learning to Theorize the World from Observation ↗	Doojin Baek et al.		ICMLOral2026
152	How much can language models memorize? ↗	John Morris et al.		ICMLOral2026
153	Equivalence of Context and Parameter Updates in Modern Transformer Blocks ↗	Adrian Goldwaser et al.		ICMLOral2026
154	GoodDiffusion: Proactive Copyright Protection for Diffusion Generative Models via Learnable Sample-specific Signatures ↗	Shixi Qin et al.		ICMLOral2026
155	Focus and Dilution: The Multi-stage Learning Process of Attention ↗	Zheng-An Chen et al.		ICMLOral2026
156	FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs ↗	Rajat Vadiraj Dwaraknath et al.		ICMLOral2026
157	Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation ↗	Philip Jordan et al. Philip Jordan, Maryam Kamgarpour		ICMLOral2026
158	CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability ↗	Xianzhen Luo et al.		ICMLOral2026
159	Orthogonal Concept Erasure for Diffusion Models ↗	Yuhao Sun et al.		ICMLOral2026
160	Prescriptive Scaling Reveals the Evolution of Language Model Capabilities ↗	Hanlin Zhang et al.		ICMLOral2026
161	On the Limits of LLM Adaptability: Impact of LLM Pre-Training on Annotation Task Performance ↗	Etienne Casanova et al.		ICMLOral2026
162	Privacy-Aware Video Anomaly Detection: Guided Orthogonal Projection and a Comprehensive Evaluation Framework ↗	Wenxiang Diao et al.		ICMLOral2026
163	Procedural Pretraining: Warming Up Language Models with Abstract Data ↗	Liangze Jiang et al.		ICMLOral2026
164	Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs ↗	Wenbo Pan et al.		ICMLOral2026
165	Which Algorithms Can Graph Neural Networks Learn? ↗	Solveig Wittig et al.		ICMLOral2026
166	What Preferences Can—and Cannot—Predict in Multi-Agent Online Learning ↗	Omar Abbadi et al.		ICMLOral2026
167	OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration ↗	Shijun Li et al.		ICMLOral2026
168	SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients ↗	Anselm Paulus et al.		ICMLOral2026
1	Revenue Efficiency of Correlated Equilibria in First Price Auctions	Anders Bo Ipsen	Aarhus U	ICMLSpotlight2026
2	DecodeShare: Tracing the Shared Pathways of LLM Decode-Time Decisions	Bruce Shao	Wake Forest U	ICMLSpotlight2026
3	Online Conformal Prediction via Universal Portfolio Algorithms	Tuo Liu	UPenn	ICMLSpotlight2026
4	Optimal Decision-Making Based on Prediction Sets	Yuting Wang	UPenn	ICMLSpotlight2026
5	Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases	Min et al.	UPenn	ICMLSpotlight2026
6	When to Trust the Cheap Check: Weak and Strong Verification for Reasoning	Shayan Kiyani	UPenn	ICMLSpotlight2026
7	Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off	Maaya Sakata	U Tsukuba / RIKEN AIP	ICMLSpotlight2026
8	SVRG and Beyond via Posterior Correction	Nico Daheim	TU Darmstadt / hessian.AI	ICMLSpotlight2026
9	Position: No Retroactive Cure for Infringement during Training	Satoru Utsunomiya	U Tokyo	ICMLSpotlight2026
1	Generalized Linear Mode Connectivity for Transformers ↗	Alexander Theus et al.	ETHZ - ETH Zurich	NeurIPSOral2025
2	Deep Compositional Phase Diffusion for Long Motion Sequence Generation ↗	Ho Yin Au et al.	Hong Kong Baptist University	NeurIPSOral2025
3	GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability ↗	Burouj Armgaan et al.	Indian Institute of Technology Delhi	NeurIPSOral2025
4	RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation ↗	Xingliang Wang et al.	Zhejiang University	NeurIPSOral2025
5	Agnostic Active Learning Is Always Better Than Passive Learning ↗	Steve Hanneke	Purdue University	NeurIPSOral2025
6	Learning Linear Attention in Polynomial Time ↗	Morris Yau et al.	Massachusetts Institute of Technology	NeurIPSOral2025
7	Optimal Mistake Bounds for Transductive Online Learning ↗	Zachary Chase et al.	University of California, San Diego	NeurIPSOral2025
8	State Entropy Regularization for Robust Reinforcement Learning ↗	Yonatan Ashlag et al.	Technion - Israel Institute of Technology, Technion	NeurIPSOral2025
9	On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity ↗	Quentin Bertrand et al.	INRIA	NeurIPSOral2025
10	Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training ↗	Tony Bonnaire et al.	Université Paris-Saclay	NeurIPSOral2025
11	Adjoint Schrödinger Bridge Sampler ↗	Guan-Horng Liu et al.	FAIR, Meta AI	NeurIPSOral2025
12	Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies ↗	Felix Chalumeau et al.	InstaDeep	NeurIPSOral2025
13	High-Dimensional Calibration from Swap Regret ↗	Maxwell Fishelson et al.	Massachusetts Institute of Technology	NeurIPSOral2025
14	In Search of Adam’s Secret Sauce ↗	Antonio Orvieto et al. Antonio Orvieto, Robert M. Gower	ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center, Tübingen, Germany	NeurIPSOral2025
15	An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds ↗	Siyu Chen et al.	Yale University	NeurIPSOral2025
16	MaxSup: Overcoming Representation Collapse in Label Smoothing ↗	Yuxuan Zhou et al.	Baidu	NeurIPSOral2025
17	Memory Mosaics at scale ↗	Jianyu Zhang et al. Jianyu Zhang, Leon Bottou	New York University	NeurIPSOral2025
18	The emergence of sparse attention: impact of data distribution and benefits of repetition ↗	Nicolas Zucchet et al.	ETHZ - ETH Zurich	NeurIPSOral2025
19	ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts ↗	Linfeng Tang et al.	Wuhan University	NeurIPSOral2025
20	Identifiability of Deep Polynomial Neural Networks ↗	Konstantin Usevich et al.	CNRS	NeurIPSOral2025
21	Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference ↗	Jiayi Yuan et al.	Rice University	NeurIPSOral2025
22	PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models ↗	Ruiqi Wang et al.	Purdue University	NeurIPSOral2025
23	A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders ↗	David Chanin et al.	MATS	NeurIPSOral2025
24	EvoLM: In Search of Lost Training Dynamics for Language Model Reasoning ↗	Zhenting Qi et al.	Harvard University	NeurIPSOral2025
25	Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions ↗	Zhaoxian Wu et al.	Cornell University	NeurIPSOral2025
26	Discovering Opinion Intervals from Conflicts in Signed Graphs ↗	Peter Blohm et al.	Technische Universität Wien	NeurIPSOral2025
27	A Clean Slate for Offline Reinforcement Learning ↗	Matthew Thomas Jackson et al.	Google DeepMind	NeurIPSOral2025
28	Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy ↗	Phuc Tran et al.	VinUniversity	NeurIPSOral2025
29	Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization ↗	Shogo Iwazaki	MI-6 Ltd.	NeurIPSOral2025
30	Auto-Compressing Networks ↗	Vaggelis Dorovatas et al.	National Technical University of Athens	NeurIPSOral2025
31	MokA: Multimodal Low-Rank Adaptation for MLLMs ↗	Yake Wei et al.	Renmin University of China	NeurIPSOral2025
32	Advancing Expert Specialization for Better MoE ↗	Hongcan Guo et al.	ByteDance Inc.	NeurIPSOral2025
33	From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics ↗	Zheng-An Chen et al. Zheng-An Chen, Tao Luo	Shanghai Jiaotong University	NeurIPSOral2025
34	Large Language Diffusion Models ↗	Shen Nie et al.	Renmin University of China	NeurIPSOral2025
35	Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation ↗	Wenbin An et al.	Xi'an Jiaotong University	NeurIPSOral2025
36	Interactive Cross-modal Learning for Text-3D Scene Retrieval ↗	Yanglin Feng et al.	Sichuan University	NeurIPSOral2025
37	Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation ↗	Wei Wang et al.	SUN YAT-SEN UNIVERSITY	NeurIPSOral2025
38	Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables ↗	Zhongnan Cai et al.	Xiamen University	NeurIPSOral2025
39	Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks ↗	Andrea Montanari et al.	Stanford University	NeurIPSOral2025
40	1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities ↗	Kevin Wang et al.	Princeton University	NeurIPSOral2025
41	Depth-Bounds for Neural Networks via the Braid Arrangement ↗	Moritz Leo Grillo et al.	Max-Planck Institute	NeurIPSOral2025
42	Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization ↗	Milad Sefidgaran et al.	Huawei Paris Research Center	NeurIPSOral2025
43	A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning ↗	Yuzheng Hu et al.	University of Illinois at Urbana-Champaign	NeurIPSOral2025
44	High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model ↗	Valentin Schmutz et al.	University College London, University of London	NeurIPSOral2025
45	Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks ↗	Korneel Van den Berghe et al.	Delft University of Technology	NeurIPSOral2025
46	Class-wise Balancing Data Replay for Federated Class-Incremental Learning ↗	Zhuang Qi et al.	Shandong University	NeurIPSOral2025
47	Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain ↗	Trinity Chung et al.		NeurIPSOral2025
48	ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism ↗	Zedong Liu et al.	University of Electronic Science and Technology of China	NeurIPSOral2025
49	Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks ↗	Steffen Schotthöfer et al.	Oak Ridge National Laboratory	NeurIPSOral2025
50	QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training ↗	Wei Dai et al.	Massachusetts Institute of Technology	NeurIPSOral2025
51	Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free ↗	Zihan Qiu et al.	Alibaba Group	NeurIPSOral2025
52	Learning long range dependencies through time reversal symmetry breaking ↗	Guillaume Pourcel et al.	INRIA	NeurIPSOral2025
53	FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution ↗	Qiusheng Huang et al.	Fudan University	NeurIPSOral2025
54	Superposition Yields Robust Neural Scaling ↗	Yizhou Liu et al.	Massachusetts Institute of Technology	NeurIPSOral2025
55	ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression ↗	Tom Burgert et al.	Technische Universität Berlin	NeurIPSOral2025
56	On Linear Mode Connectivity of Mixture-of-Experts Architectures ↗	Viet-Hoang Tran et al.	National University of Singapore	NeurIPSOral2025
57	OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model ↗	Zhenhao Zhang et al.		NeurIPSOral2025
58	Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think ↗	Ge Wu et al.	Nankai University	NeurIPSOral2025
59	Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation ↗	Zihan Wang et al.	National University of Singapore	NeurIPSOral2025
60	Learning (Approximately) Equivariant Networks via Constrained Optimization ↗	Andrei Manolache et al.	Universität Stuttgart	NeurIPSOral2025
61	SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding ↗	Yuan Zang et al.	Brown University	NeurIPSOral2025
62	Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? ↗	Yang Yue et al.		NeurIPSOral2025
63	Learning to Learn with Contrastive Meta-Objective ↗	Shiguang Wu et al.	Tsinghua University, Tsinghua University	NeurIPSOral2025
64	KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction ↗	Jang-Hyun Kim et al.	Apple	NeurIPSOral2025
65	HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models ↗	Zelin Peng et al.	Shanghai Jiaotong University	NeurIPSOral2025
66	SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing ↗	Mingfei Chen et al.	University of Washington	NeurIPSOral2025
67	A multiscale analysis of mean-field transformers in the moderate interaction regime ↗	Giuseppe Bruno et al.	Universität Bern	NeurIPSOral2025
68	Exploring Diffusion Transformer Designs via Grafting ↗	Keshigeyan Chandrasegaran et al.	Stanford University	NeurIPSOral2025
69	Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness ↗	Thomas Pethick et al.	Swiss Federal Institute of Technology Lausanne	NeurIPSOral2025
70	Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion ↗	Qing-Yuan Jiang et al.	Nanjing University of Science and Technology	NeurIPSOral2025
71	TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability ↗	Tonglong Wei et al.	Beijing Jiaotong University	NeurIPSOral2025
72	PhySense: Sensor Placement Optimization for Accurate Physics Sensing ↗	Yuezhou Ma et al.	Tsinghua University, Tsinghua University	NeurIPSOral2025
73	InfinityStar: Uniﬁed Spacetime AutoRegressive Modeling for Visual Generation ↗	Jinlai Liu et al.	ByteDance Inc.	NeurIPSOral2025
74	Does Stochastic Gradient really succeed for bandits? ↗	Dorian Baudry et al.	INRIA	NeurIPSOral2025
75	Perception Encoder: The best visual embeddings are not at the output of the network ↗	Daniel Bolya et al.	Meta	NeurIPSOral2025
76	PlayerOne: Egocentric World Simulator ↗	Yuanpeng Tu et al.	The University of Hong Kong	NeurIPSOral2025
77	Mean Flows for One-step Generative Modeling ↗	Zhengyang Geng et al.	Carnegie Mellon University	NeurIPSOral2025
1	MoCha: Towards Movie-Grade Talking Character Generation ↗	Cong Wei et al.		NeurIPSSpotlight2025
2	WISA: World simulator assistant for physics-aware text-to-video generation ↗	Jing Wang et al.		NeurIPSSpotlight2025
3	ModHiFi: Identifying High Fidelity predictive components for Model Modification ↗	Dhruva Kashyap et al.		NeurIPSSpotlight2025
4	The Structure of Relation Decoding Linear Operators in Large Language Models ↗	Miranda Anna Christ et al.		NeurIPSSpotlight2025
5	KLASS: KL-Guided Fast Inference in Masked Diffusion Models ↗	Seo Hyun Kim et al.		NeurIPSSpotlight2025
6	HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models ↗	Yu Zhou et al.		NeurIPSSpotlight2025
7	Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models ↗	Aleksandar Terzic et al.		NeurIPSSpotlight2025
8	Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning ↗	Chaofan Lin et al.		NeurIPSSpotlight2025
9	An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation ↗	UZAIR AKBAR et al.		NeurIPSSpotlight2025
10	Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery ↗	Zhe Zhao et al.		NeurIPSSpotlight2025
11	OpenCUA: Open Foundations for Computer-Use Agents ↗	Xinyuan Wang et al.		NeurIPSSpotlight2025
12	Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models ↗	Ehsan Sharifian et al.		NeurIPSSpotlight2025
13	Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning ↗	Alexander Bodard et al.		NeurIPSSpotlight2025
14	Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models ↗	Zekai Zhao et al.		NeurIPSSpotlight2025
15	Direct Fisher Score Estimation for Likelihood Maximization ↗	Sherman Khoo et al.		NeurIPSSpotlight2025
16	Path-Enhanced Contrastive Learning for Recommendation ↗	Haoran Sun et al.		NeurIPSSpotlight2025
17	T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning ↗	Julie Mordacq et al.		NeurIPSSpotlight2025
18	Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks ↗	Heasung Kim et al.		NeurIPSSpotlight2025
19	AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play ↗	Ran Xu et al.		NeurIPSSpotlight2025
20	DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method ↗	Qingwen Zhang et al.		NeurIPSSpotlight2025
21	Web-Shepherd: Advancing PRMs for Reinforcing Web Agents ↗	Hyungjoo Chae et al.		NeurIPSSpotlight2025
22	How do Transformers Learn Implicit Reasoning? ↗	Jiaran Ye et al.		NeurIPSSpotlight2025
23	On the sample complexity of semi-supervised multi-objective learning ↗	Tobias Wegel et al.		NeurIPSSpotlight2025
24	Diversity-Aware Policy Optimization for Large Language Model Reasoning ↗	Jian Yao et al.		NeurIPSSpotlight2025
25	Fixed-Point RNNs: Interpolating from Diagonal to Dense ↗	Sajad Movahedi et al.		NeurIPSSpotlight2025
26	Bridging Theory and Practice in Link Representation with Graph Neural Networks ↗	Veronica Lachi et al.		NeurIPSSpotlight2025
27	ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space ↗	Chuanchao Zang et al.		NeurIPSSpotlight2025
28	Protein Design with Dynamic Protein Vocabulary ↗	Nuowei Liu et al.		NeurIPSSpotlight2025
29	Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning ↗	Sanghyun Ahn et al.		NeurIPSSpotlight2025
30	AI-Researcher: Autonomous Scientific Innovation ↗	Jiabin Tang et al.		NeurIPSSpotlight2025
31	Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency ↗	Renzhao Liang et al.		NeurIPSSpotlight2025
32	DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation ↗	Kefei Zhu et al.		NeurIPSSpotlight2025
33	Learning Robust Vision-Language Models from Natural Latent Spaces ↗	Zhangyun Wang et al.		NeurIPSSpotlight2025
34	Accelerating Diffusion LLMs via Adaptive Parallel Decoding ↗	Daniel Mingyi Israel et al.		NeurIPSSpotlight2025
35	Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination ↗	Rakshit Trivedi et al.		NeurIPSSpotlight2025
36	Graph-Based Attention for Differentiable MaxSAT Solving ↗	Sota Moriyama et al. Sota Moriyama, Katsumi Inoue		NeurIPSSpotlight2025
37	Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems ↗	Christian Walder et al.		NeurIPSSpotlight2025
38	LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data ↗	Zehao Wang et al.		NeurIPSSpotlight2025
39	Multitask Learning with Stochastic Interpolants ↗	Hugo Negrel et al.		NeurIPSSpotlight2025
40	FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities ↗	Jin Wang et al.		NeurIPSSpotlight2025
41	Fast MRI for All: Bridging Access Gaps by Training without Raw Data ↗	Yasar Utku Alcalar et al.		NeurIPSSpotlight2025
42	Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better ↗	Danny Driess et al.		NeurIPSSpotlight2025
43	Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning ↗	Yang Chen et al.		NeurIPSSpotlight2025
44	ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation ↗	Jiatong Shi et al.		NeurIPSSpotlight2025
45	Projective Equivariant Networks via Second-order Fundamental Differential Invariants ↗	Yikang Li et al.		NeurIPSSpotlight2025
46	ZeroS: Zero‑Sum Linear Attention for Efficient Transformers ↗	Jiecheng Lu et al.		NeurIPSSpotlight2025
47	Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models ↗	Aloni Cohen		NeurIPSSpotlight2025
48	Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates ↗	Seunghyeok Shin et al.		NeurIPSSpotlight2025
49	From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers ↗	Ryotaro Kawata et al.		NeurIPSSpotlight2025
50	Learning Interestingness in Automated Mathematical Theory Formation ↗	George Tsoukalas et al.		NeurIPSSpotlight2025
51	DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm ↗	Xiaowei Zhu et al.		NeurIPSSpotlight2025
52	Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation ↗	David Heineman et al.		NeurIPSSpotlight2025
53	Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning ↗	Idan Attias et al.		NeurIPSSpotlight2025
54	The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis ↗	Alex Lewandowski et al.		NeurIPSSpotlight2025
55	Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment ↗	Chen Liu et al.		NeurIPSSpotlight2025
56	On the Hardness of Conditional Independence Testing In Practice ↗	Zheng He et al.		NeurIPSSpotlight2025
57	Emergence and Evolution of Interpretable Concepts in Diffusion Models ↗	Berk Tinaz et al.		NeurIPSSpotlight2025
58	PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning ↗	Mingqi Wu et al.		NeurIPSSpotlight2025
59	Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics ↗	Sean McGrath et al.		NeurIPSSpotlight2025
60	GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution ↗	Fengxiang Wang et al.		NeurIPSSpotlight2025
61	Environment Inference for Learning Generalizable Dynamical System ↗	Shixuan Liu et al.		NeurIPSSpotlight2025
62	Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty ↗	Chenxi Ji et al.		NeurIPSSpotlight2025
63	Inference-Time Reward Hacking in Large Language Models ↗	Hadi Khalaf et al.		NeurIPSSpotlight2025
64	High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search ↗	Xilin Xia et al.		NeurIPSSpotlight2025
65	ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge ↗	Manh Cuong Dao et al.		NeurIPSSpotlight2025
66	Go With the Flow: Fast Diffusion for Gaussian Mixture Models ↗	George Rapakoulias et al.		NeurIPSSpotlight2025
67	SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation ↗	Enzhi Zhang et al.		NeurIPSSpotlight2025
68	ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs ↗	Landon Butler et al.		NeurIPSSpotlight2025
69	Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment ↗	Woojun Kim et al. Woojun Kim, Katia P. Sycara		NeurIPSSpotlight2025
70	OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts ↗	Shiting Xiao et al.		NeurIPSSpotlight2025
71	Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations ↗	Brian Siyuan Zheng et al.		NeurIPSSpotlight2025
72	Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems ↗	Ni Zhang et al. Ni Zhang, Zhiguang Cao		NeurIPSSpotlight2025
73	Feedback-Aware MCTS for Goal-Oriented Information Seeking ↗	Harshita Chopra et al. Harshita Chopra, Chirag Shah		NeurIPSSpotlight2025
74	Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals ↗	Stefan Stojanov et al.		NeurIPSSpotlight2025
75	Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning ↗	Tianxing Wu et al.		NeurIPSSpotlight2025
76	OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement ↗	Ye Tian et al.		NeurIPSSpotlight2025
77	Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs ↗	Masahiro Kaneko et al. Masahiro Kaneko, Timothy Baldwin		NeurIPSSpotlight2025
78	Characterizing control between interacting subsystems with deep Jacobian estimation ↗	Adam Joseph Eisen et al.		NeurIPSSpotlight2025
79	Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings ↗	Evan Markou et al.		NeurIPSSpotlight2025
80	Selective Omniprediction and Fair Abstention ↗	Sílvia Casacuberta et al.		NeurIPSSpotlight2025
81	Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models ↗	Ilias Diakonikolas et al.		NeurIPSSpotlight2025
82	A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding ↗	Alexander Koujianos Goldberg et al.		NeurIPSSpotlight2025
83	Error Forcing in Recurrent Neural Networks ↗	A Erdem Sağtekin et al.		NeurIPSSpotlight2025
84	Aligning Text-to-Image Diffusion Models to Human Preference by Classification ↗	Longquan Dai et al.		NeurIPSSpotlight2025
85	Sketched Gaussian Mechanism for Private Federated Learning ↗	Qiaobo Li et al.		NeurIPSSpotlight2025
86	Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning ↗	Hugues Van Assel et al.		NeurIPSSpotlight2025
87	Accelerating data-driven algorithm selection for combinatorial partitioning problems ↗	Vaggos Chatziafratis et al.		NeurIPSSpotlight2025
88	Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner ↗	Runa Eschenhagen et al.		NeurIPSSpotlight2025
89	Replicable Distribution Testing ↗	Ilias Diakonikolas et al.		NeurIPSSpotlight2025
90	FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction ↗	Ruizhe Zheng et al.		NeurIPSSpotlight2025
91	Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems ↗	Hao Liang et al.		NeurIPSSpotlight2025
92	Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees ↗	Daniel Ovalle et al.		NeurIPSSpotlight2025
93	Why Do Some Language Models Fake Alignment While Others Don't? ↗	Abhay Sheshadri et al.		NeurIPSSpotlight2025
94	⁠When Data Can't Meet: Estimating Correlation Across Privacy Barriers ↗	Abhinav Chakraborty et al.		NeurIPSSpotlight2025
95	TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence ↗	Feng Jiang et al.		NeurIPSSpotlight2025
96	Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences ↗	Joshua Ashkinaze et al.		NeurIPSSpotlight2025
97	Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks ↗	Ali Hariri et al.		NeurIPSSpotlight2025
98	Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems ↗	Lorenzo Baldassari et al.		NeurIPSSpotlight2025
99	Transferring Linear Features Across Language Models With Model Stitching ↗	Alan Chen et al.		NeurIPSSpotlight2025
100	Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning ↗	Navita Goyal et al.		NeurIPSSpotlight2025
101	Ambient Proteins - Training Diffusion Models on Noisy Structures ↗	Giannis Daras et al.		NeurIPSSpotlight2025
102	On Universality Classes of Equivariant Networks ↗	Marco Pacini et al.		NeurIPSSpotlight2025
103	Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions ↗	Dionysis Arvanitakis et al.		NeurIPSSpotlight2025
104	Checklists Are Better Than Reward Models For Aligning Language Models ↗	Vijay Viswanathan et al.		NeurIPSSpotlight2025
105	Blackbox Model Provenance via Palimpsestic Membership Inference ↗	Rohith Kuditipudi et al.		NeurIPSSpotlight2025
106	Scaling can lead to compositional generalization ↗	Florian Redhardt et al.		NeurIPSSpotlight2025
107	Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning ↗	Jaehun Jung et al.		NeurIPSSpotlight2025
108	AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection ↗	Saleh Momeni et al.		NeurIPSSpotlight2025
109	Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning ↗	Riccardo De Santi et al.		NeurIPSSpotlight2025
110	What Expressivity Theory Misses: Message Passing Complexity for GNNs ↗	Niklas Kemper et al.		NeurIPSSpotlight2025
111	Ambient Diffusion Omni: Training Good Models with Bad Data ↗	Giannis Daras et al.		NeurIPSSpotlight2025
112	UMA: A Family of Universal Models for Atoms ↗	Brandon M Wood et al.		NeurIPSSpotlight2025
113	The Best Instruction-Tuning Data are Those That Fit ↗	Dylan Zhang et al. Dylan Zhang, Qirun Dai, Hao Peng		NeurIPSSpotlight2025
114	Forecasting in Offline Reinforcement Learning for Non-stationary Environments ↗	Suzan Ece Ada et al.		NeurIPSSpotlight2025
115	Purifying Approximate Differential Privacy with Randomized Post-processing ↗	Yingyu Lin et al.		NeurIPSSpotlight2025
116	Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference ↗	Denis Blessing et al.		NeurIPSSpotlight2025
117	How Well Can Differential Privacy Be Audited in One Run? ↗	Amit Keinan et al.		NeurIPSSpotlight2025
118	Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning ↗	Ezgi Korkmaz		NeurIPSSpotlight2025
119	Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models ↗	Jipeng Li et al. Jipeng Li, Yanning Shen		NeurIPSSpotlight2025
120	An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination ↗	Sukanya Patra et al. Sukanya Patra, Souhaib Ben Taieb		NeurIPSSpotlight2025
121	SHAP values via sparse Fourier representation ↗	Ali Gorji et al.		NeurIPSSpotlight2025
122	Quantum Doubly Stochastic Transformers ↗	Jannis Born et al.		NeurIPSSpotlight2025
123	Reverse Engineering Human Preferences with Reinforcement Learning ↗	Lisa Alazraki et al.		NeurIPSSpotlight2025
124	Efficient Fairness-Performance Pareto Front Computation ↗	Mark Kozdoba et al.		NeurIPSSpotlight2025
125	Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity ↗	Hugo Ninou et al.		NeurIPSSpotlight2025
126	ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets ↗	Bohdan Turbal et al.		NeurIPSSpotlight2025
127	Head Pursuit: Probing Attention Specialization in Multimodal Transformers ↗	Lorenzo Basile et al.		NeurIPSSpotlight2025
128	Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations ↗	Kaibo Wang et al.		NeurIPSSpotlight2025
129	Credal Prediction based on Relative Likelihood ↗	Timo Löhr et al.		NeurIPSSpotlight2025
130	The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination ↗	Adam Klivans et al.		NeurIPSSpotlight2025
131	Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators ↗	Albert Matveev et al.		NeurIPSSpotlight2025
132	Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling ↗	Javier E. Santos et al.		NeurIPSSpotlight2025
133	CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D ↗	Francis Rhys Ward et al.		NeurIPSSpotlight2025
134	An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models ↗	Binxu Wang et al. Binxu Wang, Cengiz Pehlevan		NeurIPSSpotlight2025
135	DeepHalo: A Neural Choice Model with Controllable Context Effects ↗	Shuhan Zhang et al.		NeurIPSSpotlight2025
136	Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration ↗	Kyriakos Lotidis et al.		NeurIPSSpotlight2025
137	Quantum speedup of non-linear Monte Carlo problems ↗	Jose Blanchet et al.		NeurIPSSpotlight2025
138	Fine-grained List-wise Alignment for Generative Medication Recommendation ↗	Chenxiao Fan et al.		NeurIPSSpotlight2025
139	Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach ↗	Jonas Geiping et al.		NeurIPSSpotlight2025
140	Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics ↗	Tobias Würth et al.		NeurIPSSpotlight2025
141	Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining ↗	Raghuveer Thirukovalluru et al.		NeurIPSSpotlight2025
142	Dynamic Algorithm for Explainable $k$-medians Clustering under $\ell_p$ Norm ↗	Konstantin Makarychev et al.		NeurIPSSpotlight2025
143	Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs ↗	Mantas Mazeika et al.		NeurIPSSpotlight2025
144	Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers ↗	Florence Regol et al.		NeurIPSSpotlight2025
145	SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training ↗	Jintao Zhang et al.		NeurIPSSpotlight2025
146	Eluder dimension: localise it! ↗	Alireza Bakhtiari et al.		NeurIPSSpotlight2025
147	Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo ↗	Zachary Charles et al.		NeurIPSSpotlight2025
148	FlashMD: long-stride, universal prediction of molecular dynamics ↗	Filippo Bigi et al.		NeurIPSSpotlight2025
149	Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting ↗	Yuxuan Yang et al.		NeurIPSSpotlight2025
150	3D Equivariant Visuomotor Policy Learning via Spherical Projection ↗	Boce Hu et al.		NeurIPSSpotlight2025
151	Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs ↗	Houyi Li et al.		NeurIPSSpotlight2025
152	Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees ↗	Sangwoo Park et al.		NeurIPSSpotlight2025
153	Ridge Boosting is Both Robust and Efficient ↗	David Bruns-Smith et al.		NeurIPSSpotlight2025
154	A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning ↗	Zechen Wu et al.		NeurIPSSpotlight2025
155	Generalizable Reasoning through Compositional Energy Minimization ↗	Alexandru Oarga et al. Alexandru Oarga, Yilun Du		NeurIPSSpotlight2025
156	Universal Sequence Preconditioning ↗	Annie Marsden et al. Annie Marsden, Elad Hazan		NeurIPSSpotlight2025
157	Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles ↗	Jiangjie Chen et al.		NeurIPSSpotlight2025
158	Memory-Enhanced Neural Solvers for Routing Problems ↗	Felix Chalumeau et al.		NeurIPSSpotlight2025
159	Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition ↗	Yu Li et al.		NeurIPSSpotlight2025
160	Two Heads are Better than One: Simulating Large Transformers with Small Ones ↗	Hantao Yu et al. Hantao Yu, Josh Alman		NeurIPSSpotlight2025
161	Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span ↗	Heeseung Yun et al.		NeurIPSSpotlight2025
162	Unifying Proportional Fairness in Centroid and Non-Centroid Clustering ↗	Benjamin Cookson et al.		NeurIPSSpotlight2025
163	ARIA: Training Language Agents with Intention-driven Reward Aggregation ↗	Ruihan Yang et al.		NeurIPSSpotlight2025
164	Reasoning Planning for Language Models ↗	Bao Nguyen et al.		NeurIPSSpotlight2025
165	When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners ↗	Weixiang Zhao et al.		NeurIPSSpotlight2025
166	EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting ↗	Bohao Liao et al.		NeurIPSSpotlight2025
167	Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs ↗	Mehran Shakerinava et al.		NeurIPSSpotlight2025
168	Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples ↗	Shiva Sreeram et al.		NeurIPSSpotlight2025
169	Understanding Prompt Tuning and In-Context Learning via Meta-Learning ↗	Tim Genewein et al.		NeurIPSSpotlight2025
170	Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism ↗	Mete Erdogan et al.		NeurIPSSpotlight2025
171	On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks ↗	Mingze Wang et al. Mingze Wang, Weinan E		NeurIPSSpotlight2025
172	TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs ↗	Parjanya Prajakta Prashant et al.		NeurIPSSpotlight2025
173	Streaming Attention Approximation via Discrepancy Theory ↗	Ekaterina Kochetkova et al.		NeurIPSSpotlight2025
174	SegMASt3R: Geometry Grounded Segment Matching ↗	Rohit Jayanti et al.		NeurIPSSpotlight2025
175	Among Us: A Sandbox for Measuring and Detecting Agentic Deception ↗	Satvik Golechha et al.		NeurIPSSpotlight2025
176	AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling ↗	Zhining Zhang et al.		NeurIPSSpotlight2025
177	Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few ↗	Qishuai Wen et al.		NeurIPSSpotlight2025
178	EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks ↗	Rikuto Kotoge et al.		NeurIPSSpotlight2025
179	Product Distribution Learning with Imperfect Advice ↗	Arnab Bhattacharyya et al.		NeurIPSSpotlight2025
180	RoboScape: Physics-informed Embodied World Model ↗	Yu Shang et al.		NeurIPSSpotlight2025
181	InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection ↗	Jinguo Luo et al.		NeurIPSSpotlight2025
182	ARM: Adaptive Reasoning Model ↗	Siye Wu et al.		NeurIPSSpotlight2025
183	Computational Efficiency under Covariate Shift in Kernel Ridge Regression ↗	Andrea Della Vecchia et al.		NeurIPSSpotlight2025
184	Self-Assembling Graph Perceptrons ↗	Jialong Chen et al.		NeurIPSSpotlight2025
185	Scaling and context steer LLMs along the same computational path as the human brain ↗	Joséphine Raugel et al.		NeurIPSSpotlight2025
186	InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models ↗	Yanggan Gu et al.		NeurIPSSpotlight2025
187	SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios ↗	Lingwei Dang et al.		NeurIPSSpotlight2025
188	HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions ↗	Rafael Bischof et al.		NeurIPSSpotlight2025
189	RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models ↗	Junda Zhu et al.		NeurIPSSpotlight2025
190	Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens ↗	Xixian Yong et al.		NeurIPSSpotlight2025
191	Hyperbolic Fine-Tuning for Large Language Models ↗	Menglin Yang et al.		NeurIPSSpotlight2025
192	Deep Continuous-Time State-Space Models for Marked Event Sequences ↗	Yuxin Chang et al.		NeurIPSSpotlight2025
193	HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs ↗	Ningning CHEN et al.		NeurIPSSpotlight2025
194	Which Algorithms Have Tight Generalization Bounds? ↗	Michael Gastpar et al.		NeurIPSSpotlight2025
195	Axial Neural Networks for Dimension-Free Foundation Models ↗	Hyunsu Kim et al.		NeurIPSSpotlight2025
196	Horizon Reduction Makes RL Scalable ↗	Seohong Park et al.		NeurIPSSpotlight2025
197	OpenBox: Annotate Any Bounding Boxes in 3D ↗	In-Jae Lee et al.		NeurIPSSpotlight2025
198	SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image Classification ↗	Hsi-Ling Chen et al.		NeurIPSSpotlight2025
199	FFN Fusion: Rethinking Sequential Computation in Large Language Models ↗	Akhiad Bercovich et al.		NeurIPSSpotlight2025
200	Distilling LLM Agent into Small Models with Retrieval and Code Tools ↗	Minki Kang et al.		NeurIPSSpotlight2025
201	Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models ↗	Jun Zhao et al.		NeurIPSSpotlight2025
202	Differentiable Decision Tree via "ReLU+Argmin" Reformulation ↗	Qiangqiang Mao et al.		NeurIPSSpotlight2025
203	SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning ↗	Borong Zhang et al.		NeurIPSSpotlight2025
204	3D Interaction Geometric Pre-training for Molecular Relational Learning ↗	Namkyeong Lee et al.		NeurIPSSpotlight2025
205	Improved Bounds for Swap Multicalibration and Swap Omniprediction ↗	Haipeng Luo et al.		NeurIPSSpotlight2025
206	UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems ↗	Dian Meng et al.		NeurIPSSpotlight2025
207	Simultaneous Swap Regret Minimization via KL-Calibration ↗	Haipeng Luo et al.		NeurIPSSpotlight2025
208	Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints ↗	Dongjie Yang et al.		NeurIPSSpotlight2025
209	Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers? ↗	Yihao Li et al.		NeurIPSSpotlight2025
210	Probing Neural Combinatorial Optimization Models ↗	Zhiqin Zhang et al.		NeurIPSSpotlight2025
211	A Principled Path to Fitted Distributional Evaluation ↗	Sungee Hong et al.		NeurIPSSpotlight2025
212	Improving LLM General Preference Alignment via Optimistic Online Mirror Descent ↗	Yuheng Zhang et al.		NeurIPSSpotlight2025
213	Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities ↗	Tara Akhound-Sadegh et al.		NeurIPSSpotlight2025
214	Compositional Monte Carlo Tree Diffusion for Extendable Planning ↗	Jaesik Yoon et al.		NeurIPSSpotlight2025
215	Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning ↗	Jaesik Yoon et al.		NeurIPSSpotlight2025
216	Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework ↗	Ali Zafari et al.		NeurIPSSpotlight2025
217	Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness ↗	Yuheng Zhao et al.		NeurIPSSpotlight2025
218	A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search ↗	Arnav Kumar Jain et al.		NeurIPSSpotlight2025
219	MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series ↗	Payal Mohapatra et al.		NeurIPSSpotlight2025
220	Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL ↗	Xingyu Chen et al.		NeurIPSSpotlight2025
221	On the Universal Near Optimality of Hedge in Combinatorial Settings ↗	Zhiyuan Fan et al.		NeurIPSSpotlight2025
222	Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift ↗	Yi Zhang et al. Yi Zhang, Elynn Chen, Yujun Yan		NeurIPSSpotlight2025
223	Transformer brain encoders explain human high-level visual responses ↗	Hossein Adeli et al.		NeurIPSSpotlight2025
224	Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning ↗	Yeongbin Seo et al.		NeurIPSSpotlight2025
225	MoBA: Mixture of Block Attention for Long-Context LLMs ↗	Enzhe Lu et al.		NeurIPSSpotlight2025
226	DERD-Net: Learning Depth from Event-based Ray Densities ↗	Diego de Oliveira Hitzges et al.		NeurIPSSpotlight2025
227	Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models ↗	Xinran Wang et al.		NeurIPSSpotlight2025
228	VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information ↗	Zecheng Wang et al.		NeurIPSSpotlight2025
229	MoCha: Towards Movie-Grade Talking Character Generation ↗	Cong Wei et al.		NeurIPSSpotlight2025
230	Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon ↗	Tongtong Liang et al.		NeurIPSSpotlight2025
231	Fisher meets Feynman: score-based variational inference with a product of experts ↗	Diana Cai et al.		NeurIPSSpotlight2025
232	Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy ↗	Xiang Li et al.		NeurIPSSpotlight2025
233	Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics ↗	Minseok Jeong et al.		NeurIPSSpotlight2025
234	Spectral Estimation with Free Decompression ↗	Siavash Ameli et al.		NeurIPSSpotlight2025
235	CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching ↗	Chen Chen et al.		NeurIPSSpotlight2025
236	Training-Free Constrained Generation With Stable Diffusion Models ↗	Stefano Zampini et al.		NeurIPSSpotlight2025
237	Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games ↗	Soumita Hait et al.		NeurIPSSpotlight2025
238	X-Field: A Physically Informed Representation for 3D X-ray Reconstruction ↗	Feiran Wang et al.		NeurIPSSpotlight2025
239	Distillation Robustifies Unlearning ↗	Bruce W. Lee et al.		NeurIPSSpotlight2025
240	SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds ↗	Xiaokang Ye et al.		NeurIPSSpotlight2025
241	Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion ↗	Haoyu Li et al.		NeurIPSSpotlight2025
242	The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games ↗	Ioannis Anagnostides et al.		NeurIPSSpotlight2025
243	On Traceability in $\ell_p$ Stochastic Convex Optimization ↗	Sasha Voitovych et al.		NeurIPSSpotlight2025
244	Improved Representation Steering for Language Models ↗	Zhengxuan Wu et al.		NeurIPSSpotlight2025
245	FlexOLMo: Open Language Models for Flexible Data Use ↗	Weijia Shi et al.		NeurIPSSpotlight2025
246	The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization ↗	Yihua Zhang et al.		NeurIPSSpotlight2025
247	Enhancing Training Data Attribution with Representational Optimization ↗	Weiwei Sun et al.		NeurIPSSpotlight2025
248	DisMo: Disentangled Motion Representations for Open-World Motion Transfer ↗	Thomas Ressler-Antal et al.		NeurIPSSpotlight2025
249	Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction ↗	Samuel Li et al.		NeurIPSSpotlight2025
250	Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization ↗	Shaohan Li et al.		NeurIPSSpotlight2025
251	Dense Associative Memory with Epanechnikov Energy ↗	Benjamin Hoover et al.		NeurIPSSpotlight2025
252	Searching Latent Program Spaces ↗	Matthew Macfarlane et al.		NeurIPSSpotlight2025
253	Convergence Rates of Constrained Expected Improvement ↗	Haowei Wang et al.		NeurIPSSpotlight2025
254	CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision ↗	Awni Altabaa et al.		NeurIPSSpotlight2025
255	Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time ↗	Daniel D. Richman et al.		NeurIPSSpotlight2025
256	QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models ↗	Yutong Wang et al.		NeurIPSSpotlight2025
257	Caption This, Reason That: VLMs Caught in the Middle ↗	Zihan Weng et al.		NeurIPSSpotlight2025
258	Universal Causal Inference in a Topos ↗	Sridhar Mahadevan		NeurIPSSpotlight2025
259	Can We Infer Confidential Properties of Training Data from LLMs? ↗	Pengrun Huang et al.		NeurIPSSpotlight2025
260	Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes ↗	Itamar Harel et al.		NeurIPSSpotlight2025
261	Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models ↗	Chantal Shaib et al.		NeurIPSSpotlight2025
262	Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems ↗	Elfarouk Harb et al.		NeurIPSSpotlight2025
263	Private Set Union with Multiple Contributions ↗	Travis Dick et al.		NeurIPSSpotlight2025
264	Clustering via Hedonic Games: New Concepts and Algorithms ↗	Gergely Csáji et al.		NeurIPSSpotlight2025
265	The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis ↗	Hoang Pham et al.		NeurIPSSpotlight2025
266	Fast Training of Large Kernel Models with Delayed Projections ↗	Amirhesam Abedsoltan et al.		NeurIPSSpotlight2025
267	d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning ↗	Siyan Zhao et al.		NeurIPSSpotlight2025
268	Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance ↗	Qiujiang Jin et al. Qiujiang Jin, Aryan Mokhtari		NeurIPSSpotlight2025
269	Extrapolation by Association: Length Generalization Transfer In Transformers ↗	Ziyang Cai et al.		NeurIPSSpotlight2025
270	Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff ↗	Eric Lei et al.		NeurIPSSpotlight2025
271	Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness ↗	Longwei Wang et al.		NeurIPSSpotlight2025
272	Color Conditional Generation with Sliced Wasserstein Guidance ↗	Alexander Lobashev et al.		NeurIPSSpotlight2025
273	Private Hyperparameter Tuning with Ex-Post Guarantee ↗	Badih Ghazi et al.		NeurIPSSpotlight2025
274	A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning ↗	Guan Zhe Hong et al.		NeurIPSSpotlight2025
275	Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling ↗	Yufan Li et al. Yufan Li, Pragya Sur		NeurIPSSpotlight2025
276	Reconstruction and Secrecy under Approximate Distance Queries ↗	Shay Moran et al. Shay Moran, Elizaveta Nesterova		NeurIPSSpotlight2025
277	Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs ↗	Hao Kang et al.		NeurIPSSpotlight2025
278	Characterizing the Expressivity of Fixed-Precision Transformer Language Models ↗	Jiaoda Li et al. Jiaoda Li, Ryan Cotterell		NeurIPSSpotlight2025
279	Distributional Training Data Attribution: What do Influence Functions Sample? ↗	Bruno Kacper Mlodozeniec et al.		NeurIPSSpotlight2025
280	Hogwild! Inference: Parallel LLM Generation via Concurrent Attention ↗	Gleb Rodionov et al.		NeurIPSSpotlight2025
281	Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation ↗	Abdelrahman Eldesokey et al.		NeurIPSSpotlight2025
282	The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability? ↗	Denis Sutter et al.		NeurIPSSpotlight2025
283	Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS ↗	Tao Wang et al.		NeurIPSSpotlight2025
284	Generalized Top-k Mallows Model for Ranked Choices ↗	Shahrzad Haddadan et al. Shahrzad Haddadan, Sara Ahmadian		NeurIPSSpotlight2025
285	Improving Bilinear RNN with Closed-loop Control ↗	Jiaxi Hu et al.		NeurIPSSpotlight2025
286	Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence ↗	Diankun Wu et al.		NeurIPSSpotlight2025
287	SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation ↗	Claudia Cuttano et al.		NeurIPSSpotlight2025
288	Cost-Aware Contrastive Routing for LLMs ↗	Reza Shirkavand et al.		NeurIPSSpotlight2025
289	Is Grokking a Computational Glass Relaxation? ↗	Xiaotian Zhang et al.		NeurIPSSpotlight2025
290	LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers ↗	Liting Lin et al.		NeurIPSSpotlight2025
291	On the necessity of adaptive regularisation: Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls ↗	Emmeran Johnson et al.		NeurIPSSpotlight2025
292	Controlling Thinking Speed in Reasoning Models ↗	Zhengkai Lin et al.		NeurIPSSpotlight2025
293	Vector Quantization in the Brain: Grid-like Codes in World Models ↗	Xiangyuan Peng et al.		NeurIPSSpotlight2025
294	IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning ↗	Xiong Zhang et al.		NeurIPSSpotlight2025
295	Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws ↗	Lin Guo et al.		NeurIPSSpotlight2025
296	MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation ↗	Ziru Wang et al.		NeurIPSSpotlight2025
297	SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation ↗	Zekun Qi et al.		NeurIPSSpotlight2025
298	Conditional Representation Learning for Customized Tasks ↗	Honglin Liu et al.		NeurIPSSpotlight2025
299	Angular Steering: Behavior Control via Rotation in Activation Space ↗	Hieu M. Vu et al. Hieu M. Vu, Tan Minh Nguyen		NeurIPSSpotlight2025
300	COOPERA: Continual Open-Ended Human-Robot Assistance ↗	Chenyang Ma et al.		NeurIPSSpotlight2025
301	Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance ↗	Ya-Wei Eileen Lin et al.		NeurIPSSpotlight2025
302	Detecting Generated Images by Fitting Natural Image Distributions ↗	Yonggang Zhang et al.		NeurIPSSpotlight2025
303	Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness ↗	Bogdan Chornomaz et al.		NeurIPSSpotlight2025
304	ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints ↗	Rui Xu et al.		NeurIPSSpotlight2025
305	Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses ↗	Yuzhou Cao et al.		NeurIPSSpotlight2025
306	Co-Reinforcement Learning for Unified Multimodal Understanding and Generation ↗	Jingjing Jiang et al.		NeurIPSSpotlight2025
307	Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models ↗	Benjamin Walker et al.		NeurIPSSpotlight2025
308	Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding ↗	Xiaoqian Shen et al.		NeurIPSSpotlight2025
309	Privacy amplification by random allocation ↗	Moshe Shenfeld et al. Moshe Shenfeld, Vitaly Feldman		NeurIPSSpotlight2025
310	Tackling Biased Evaluators in Dueling Bandits ↗	Ming Tang et al.		NeurIPSSpotlight2025
311	Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization ↗	Cong Wang et al.		NeurIPSSpotlight2025
312	Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models ↗	Chunlong Xie et al.		NeurIPSSpotlight2025
313	SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration ↗	Elif Arslan et al.		NeurIPSSpotlight2025
314	TGA: True-to-Geometry Avatar Dynamic Reconstruction ↗	Bo Guo et al.		NeurIPSSpotlight2025
315	Neighbor-aware Contrastive Disambiguation for Cross-Modal Hashing with Redundant Annotations ↗	Chao Su et al.		NeurIPSSpotlight2025
316	Minimax Adaptive Online Nonparametric Regression over Besov spaces ↗	Paul Liautaud et al.		NeurIPSSpotlight2025
317	UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection ↗	Jigang Fan et al.		NeurIPSSpotlight2025
318	URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model ↗	Zhe Li et al.		NeurIPSSpotlight2025
319	L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias ↗	jingxiao zhang et al.		NeurIPSSpotlight2025
320	Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning ↗	Gunshi Gupta et al.		NeurIPSSpotlight2025
321	Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data ↗	Tianyi Chen et al.		NeurIPSSpotlight2025
322	RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation ↗	Boyuan Cao et al.		NeurIPSSpotlight2025
323	Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws ↗	Zhixuan Pan et al.		NeurIPSSpotlight2025
324	Differentiable Hierarchical Visual Tokenization ↗	Marius Aasan et al.		NeurIPSSpotlight2025
325	Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design ↗	Yunfan Li et al. Yunfan Li, Eric Liu, Lin Yang		NeurIPSSpotlight2025
326	Meta CLIP 2: A Worldwide Scaling Recipe ↗	Yung-Sung Chuang et al.		NeurIPSSpotlight2025
327	Policy Compatible Skill Incremental Learning via Lazy Learning Interface ↗	Daehee Lee et al.		NeurIPSSpotlight2025
328	Estimating cognitive biases with attention-aware inverse planning ↗	Sounak Banerjee et al.		NeurIPSSpotlight2025
329	An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph ↗	Tam Le et al.		NeurIPSSpotlight2025
330	DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning ↗	Wenxuan Shi et al.		NeurIPSSpotlight2025
331	MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting ↗	Yumeng He et al. Yumeng He, Yunbo Wang		NeurIPSSpotlight2025
332	Towards a Pairwise Ranking Model with Orderliness and Monotonicity for Label Enhancement ↗	Yunan Lu et al.		NeurIPSSpotlight2025
333	Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping ↗	Pu Yang et al.		NeurIPSSpotlight2025
334	Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning ↗	Wenyi Xiao et al. Wenyi Xiao, Leilei Gan		NeurIPSSpotlight2025
335	Exploration via Feature Perturbation in Contextual Bandits ↗	Seouh-won Yi et al. Seouh-won Yi, Min-hwan Oh		NeurIPSSpotlight2025
336	Instance-Optimality for Private KL Distribution Estimation ↗	Jiayuan Ye et al.		NeurIPSSpotlight2025
337	DMWM: Dual-Mind World Model with Long-Term Imagination ↗	Lingyi Wang et al.		NeurIPSSpotlight2025
338	TimeWak: Temporal Chained-Hashing Watermark for Time Series Data ↗	Zhi Wen Soi et al.		NeurIPSSpotlight2025
339	UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface ↗	Hao Tang et al.		NeurIPSSpotlight2025
340	DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models ↗	Ziyi Wu et al.		NeurIPSSpotlight2025
341	Precise Asymptotics and Refined Regret of Variance-Aware UCB ↗	Yingying Fan et al.		NeurIPSSpotlight2025
342	InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions ↗	Liangjian Wen et al.		NeurIPSSpotlight2025
343	Extracting task-relevant preserved dynamics from contrastive aligned neural recordings ↗	Yiqi Jiang et al.		NeurIPSSpotlight2025
344	Orochi: Versatile Biomedical Image Processor ↗	Gaole Dai et al.		NeurIPSSpotlight2025
345	WISA: World simulator assistant for physics-aware text-to-video generation ↗	Jing Wang et al.		NeurIPSSpotlight2025
346	Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning ↗	Dravyansh Sharma et al. Dravyansh Sharma, Alec Sun		NeurIPSSpotlight2025
347	KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation ↗	Jiajun Shi et al.		NeurIPSSpotlight2025
348	Learnable Sampler Distillation for Discrete Diffusion Models ↗	Feiyang Fu et al.		NeurIPSSpotlight2025
349	On the Hardness of Approximating Distributions with Tractable Probabilistic Models ↗	John Leland et al. John Leland, YooJung Choi		NeurIPSSpotlight2025
350	MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE ↗	Zongle Huang et al.		NeurIPSSpotlight2025
351	SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement ↗	Xiyao Wang et al.		NeurIPSSpotlight2025
352	Deno-IF: Unsupervised Noisy Visible and Infrared Image Fusion Method ↗	Han Xu et al.		NeurIPSSpotlight2025
353	ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection ↗	Haowei Zhu et al.		NeurIPSSpotlight2025
354	Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues ↗	Chinmay Talegaonkar et al.		NeurIPSSpotlight2025
355	PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding ↗	Ansel Blume et al.		NeurIPSSpotlight2025
356	Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data ↗	Lingkai Kong et al.		NeurIPSSpotlight2025
357	Asymmetric Duos: Sidekicks Improve Uncertainty ↗	Tim G. Zhou et al.		NeurIPSSpotlight2025
358	Robust learning of halfspaces under log-concave marginals ↗	Jane Lange et al. Jane Lange, Arsen Vasilyan		NeurIPSSpotlight2025
359	Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data ↗	Chen Fan et al.		NeurIPSSpotlight2025
360	Lost in Transmission: When and Why LLMs Fail to Reason Globally ↗	Tobias Schnabel et al.		NeurIPSSpotlight2025
361	On Transferring Transferability: Towards a Theory for Size Generalization ↗	Eitan Levin et al.		NeurIPSSpotlight2025
362	When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization ↗	Vivek Ramanujan et al.		NeurIPSSpotlight2025
363	FlowFeat: Pixel-Dense Embedding of Motion Profiles ↗	Nikita Araslanov et al.		NeurIPSSpotlight2025
364	The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models ↗	Alex Damian et al.		NeurIPSSpotlight2025
365	Incremental Sequence Classification with Temporal Consistency ↗	Lucas Maystre et al.		NeurIPSSpotlight2025
366	LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering ↗	Jonas Kulhanek et al.		NeurIPSSpotlight2025
367	Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics ↗	Deep Patel et al.		NeurIPSSpotlight2025
368	Provable Gradient Editing of Deep Neural Networks ↗	Zhe Tao et al. Zhe Tao, Aditya V. Thakur		NeurIPSSpotlight2025
369	Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models ↗	Sreyan Ghosh et al.		NeurIPSSpotlight2025
370	RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes ↗	Fang Li et al.		NeurIPSSpotlight2025
371	Integration Matters for Learning PDEs with Backward SDEs ↗	Sungje Park et al. Sungje Park, Stephen Tu		NeurIPSSpotlight2025
372	Unleashing Hour-Scale Video Training for Long Video-Language Understanding ↗	Jingyang Lin et al.		NeurIPSSpotlight2025
373	Neural Entropy ↗	Akhil Premkumar		NeurIPSSpotlight2025
374	Locality in Image Diffusion Models Emerges from Data Statistics ↗	Artem Lukoianov et al.		NeurIPSSpotlight2025
375	Regularized least squares learning with heavy-tailed noise is minimax optimal ↗	Mattes Mollenhauer et al.		NeurIPSSpotlight2025
376	On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning ↗	Till Freihaut et al. Till Freihaut, Giorgia Ramponi		NeurIPSSpotlight2025
377	MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention ↗	Can Yaras et al.		NeurIPSSpotlight2025
378	The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness ↗	Sahar Abdelnabi et al. Sahar Abdelnabi, Ahmed Salem		NeurIPSSpotlight2025
379	Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks ↗	Ann Huang et al.		NeurIPSSpotlight2025
380	Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach ↗	Chenbei Lu et al.		NeurIPSSpotlight2025
381	AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench ↗	Edan Toledo et al.		NeurIPSSpotlight2025
382	Differentiable Cyclic Causal Discovery Under Unmeasured Confounders ↗	Muralikrishnna Guruswamy Sethuraman et al.		NeurIPSSpotlight2025
383	ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals ↗	Jonas Elsborg et al.		NeurIPSSpotlight2025
384	Compositional Neural Network Verification via Assume-Guarantee Reasoning ↗	Hai Duong et al.		NeurIPSSpotlight2025
385	A machine learning approach that beats Rubik's cubes ↗	Alexander Chervov et al.		NeurIPSSpotlight2025
386	ENMA: Tokenwise Autoregression for Continuous Neural PDE Operators ↗	Armand Kassaï Koupaï et al.		NeurIPSSpotlight2025
387	Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training ↗	William Merrill et al.		NeurIPSSpotlight2025
388	Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning ↗	Bastien Dubail et al.		NeurIPSSpotlight2025
389	Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate ↗	Ferdinand Genans et al.		NeurIPSSpotlight2025
390	Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models ↗	Tomas Soucek et al.		NeurIPSSpotlight2025
391	Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation ↗	Lucas Morisset et al.		NeurIPSSpotlight2025
392	Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration ↗	Thomas Decker et al.		NeurIPSSpotlight2025
393	ConTextTab: A Semantics-Aware Tabular In-Context Learner ↗	Marco Spinaci et al.		NeurIPSSpotlight2025
394	Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness ↗	Mojtaba Kolahdouzi et al.		NeurIPSSpotlight2025
395	Less is More: Improving LLM Alignment via Preference Data Selection ↗	Xun Deng et al.		NeurIPSSpotlight2025
396	Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning ↗	Roger Creus Castanyer et al.		NeurIPSSpotlight2025
397	SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding ↗	Thomas Walton et al.		NeurIPSSpotlight2025
398	SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs ↗	Jinwoo Park et al.		NeurIPSSpotlight2025
399	DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models ↗	Simone Carnemolla et al.		NeurIPSSpotlight2025
400	What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains ↗	Chanakya Ekbote et al.		NeurIPSSpotlight2025
401	Sample-Adaptivity Tradeoff in On-Demand Sampling ↗	Nika Haghtalab et al.		NeurIPSSpotlight2025
402	Online Strategic Classification With Noise and Partial Feedback ↗	Tianrun Zhao et al.		NeurIPSSpotlight2025
403	Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation ↗	Guowei Wang et al.		NeurIPSSpotlight2025
404	Strategic Hypothesis Testing ↗	Yatong Chen et al.		NeurIPSSpotlight2025
405	Accelerating Optimization via Differentiable Stopping Time ↗	Zhonglin Xie et al.		NeurIPSSpotlight2025
406	Tight Generalization Bounds for Large-Margin Halfspaces ↗	Kasper Green Larsen et al.		NeurIPSSpotlight2025
407	Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis ↗	Tianrui Wang et al.		NeurIPSSpotlight2025
408	UMoE: Unifying Attention and FFN with Shared Experts ↗	Yuanhang Yang et al.		NeurIPSSpotlight2025
409	RF-Agent: Automated Reward Function Design via Language Agent Tree Search ↗	Ning Gao et al.		NeurIPSSpotlight2025
410	GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning ↗	Yeonjoon Jung et al.		NeurIPSSpotlight2025
411	Quantization-Free Autoregressive Action Transformer ↗	Ziyad Sheebaelhamd et al.		NeurIPSSpotlight2025
412	LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models ↗	Qianyue Hao et al.		NeurIPSSpotlight2025
413	BayeSQP: Bayesian Optimization through Sequential Quadratic Programming ↗	Paul Brunzema et al. Paul Brunzema, Sebastian Trimpe		NeurIPSSpotlight2025
414	Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference ↗	Álvaro Parafita et al.		NeurIPSSpotlight2025
415	AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws ↗	Oren Neumann et al. Oren Neumann, Claudius Gros		NeurIPSSpotlight2025
416	Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization ↗	He Chen et al.		NeurIPSSpotlight2025
417	The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets ↗	Yatin Dandi et al.		NeurIPSSpotlight2025
418	Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models ↗	Yue Wang et al.		NeurIPSSpotlight2025
419	OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization ↗	Hao Yuan et al.		NeurIPSSpotlight2025
420	ESCA: Contextualizing Embodied Agents via Scene-Graph Generation ↗	Jiani Huang et al.		NeurIPSSpotlight2025
421	Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback ↗	Orin Levy et al.		NeurIPSSpotlight2025
422	Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration ↗	Junyu Zhang et al.		NeurIPSSpotlight2025
423	QFFT, Question-Free Fine-Tuning for Adaptive Reasoning ↗	Wanlong Liu et al.		NeurIPSSpotlight2025
424	Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning ↗	Hongjoon Ahn et al.		NeurIPSSpotlight2025
425	Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules ↗	Binghui Li et al.		NeurIPSSpotlight2025
426	GSRF: Complex-Valued 3D Gaussian Splatting for Efficient Radio-Frequency Data Synthesis ↗	Kang Yang et al.		NeurIPSSpotlight2025
427	Sharp Gaussian approximations for Decentralized Federated Learning ↗	Soham Bonnerjee et al.		NeurIPSSpotlight2025
428	DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization ↗	Jiacai Liu et al.		NeurIPSSpotlight2025
429	MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization ↗	Da Chang et al. Da Chang, Ganzhao Yuan		NeurIPSSpotlight2025
430	Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training ↗	Qinglun Li et al.		NeurIPSSpotlight2025
431	Enhancing Contrastive Learning with Variable Similarity ↗	Haowen Cui et al.		NeurIPSSpotlight2025
432	Orient Anything V2: Unifying Orientation and Rotation Understanding ↗	Zehan Wang et al.		NeurIPSSpotlight2025
433	A Closer Look at Graph Transformers: Cross-Aggregation and Beyond ↗	Jiaming Zhuo et al.		NeurIPSSpotlight2025
434	Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution ↗	Zhanyi Sun et al. Zhanyi Sun, Shuran Song		NeurIPSSpotlight2025
435	Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models ↗	Tyler A. Chang et al. Tyler A. Chang, Ben Bergen		NeurIPSSpotlight2025
436	Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap ↗	Shixiang Liu		NeurIPSSpotlight2025
437	Continuous Thought Machines ↗	Luke Nicholas Darlow et al.		NeurIPSSpotlight2025
438	Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data ↗	Zi Liang et al.		NeurIPSSpotlight2025
439	Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting ↗	Chengqi Li et al.		NeurIPSSpotlight2025
440	Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models ↗	Lvmin Zhang et al.		NeurIPSSpotlight2025
441	CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates ↗	Tianyu Chen et al.		NeurIPSSpotlight2025
442	Predictive Preference Learning from Human Interventions ↗	Haoyuan Cai et al.		NeurIPSSpotlight2025
443	Transformers for Mixed-type Event Sequences ↗	Felix Draxler et al.		NeurIPSSpotlight2025
444	ROGR: Relightable 3D Objects using Generative Relighting ↗	Jiapeng Tang et al.		NeurIPSSpotlight2025
445	Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time ↗	Qiang Fu et al. Qiang Fu, Andre Wibisono		NeurIPSSpotlight2025
446	Cost-aware LLM-based Online Dataset Annotation ↗	Eray Can Elumar et al.		NeurIPSSpotlight2025
447	Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins ↗	Aadyot Bhatnagar et al.		NeurIPSSpotlight2025
448	STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis ↗	Jiatao Gu et al.		NeurIPSSpotlight2025
449	Flow Equivariant Recurrent Neural Networks ↗	T. Anderson Keller		NeurIPSSpotlight2025
450	AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking ↗	Xiangqi Wang et al.		NeurIPSSpotlight2025
451	LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process ↗	Huiyang Shao et al.		NeurIPSSpotlight2025
452	Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation ↗	Chen YAN et al. Chen YAN, Weina Wang, Lei Ying		NeurIPSSpotlight2025
453	On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling ↗	Moritz Haas et al.		NeurIPSSpotlight2025
454	Flash Invariant Point Attention ↗	Andrew Liu et al.		NeurIPSSpotlight2025
455	SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference ↗	Yi Zhao et al.		NeurIPSSpotlight2025
456	CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs ↗	Jan Hagnberger et al.		NeurIPSSpotlight2025
457	On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection ↗	Weiqing He et al.		NeurIPSSpotlight2025
458	Balancing Multimodal Training Through Game-Theoretic Regularization ↗	Konstantinos Kontras et al.		NeurIPSSpotlight2025
459	Bipolar Self-attention for Spiking Transformers ↗	Shuai Wang et al.		NeurIPSSpotlight2025
460	Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion ↗	Xi Zhang et al.		NeurIPSSpotlight2025
461	TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model ↗	Yichen Liu et al.		NeurIPSSpotlight2025
462	Tensor Product Attention Is All You Need ↗	Yifan Zhang et al.		NeurIPSSpotlight2025
463	TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning ↗	Sheng Wang et al.		NeurIPSSpotlight2025
464	DeCaFlow: A deconfounding causal generative model ↗	Alejandro Almodóvar et al.		NeurIPSSpotlight2025
465	Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression ↗	Yeichan Kim et al.		NeurIPSSpotlight2025
466	LLM Meeting Decision Trees on Tabular Data ↗	Hangting Ye et al.		NeurIPSSpotlight2025
467	AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement ↗	J Rosser et al.		NeurIPSSpotlight2025
468	Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing ↗	Manchao Bao et al.		NeurIPSSpotlight2025
469	MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions ↗	Pucheng Dang et al.		NeurIPSSpotlight2025
470	FP4 All the Way: Fully Quantized Training of Large Language Models ↗	Brian Chmiel et al.		NeurIPSSpotlight2025
471	Efficient Knowledge Transfer in Federated Recommendation for Joint Venture Ecosystem ↗	Yichen Li et al.		NeurIPSSpotlight2025
472	VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning ↗	Haozhe Wang et al.		NeurIPSSpotlight2025
473	Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum ↗	Snir Hordan et al.		NeurIPSSpotlight2025
474	ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding ↗	Junliang Ye et al.		NeurIPSSpotlight2025
475	The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels ↗	Yonatan Slutzky et al.		NeurIPSSpotlight2025
476	Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation ↗	Xinyu Yang et al.		NeurIPSSpotlight2025
477	BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization ↗	Qiwei Wang et al.		NeurIPSSpotlight2025
478	Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text ↗	Zhange Zhang et al.		NeurIPSSpotlight2025
479	Vision Transformers with Self-Distilled Registers ↗	Zipeng Yan et al.		NeurIPSSpotlight2025
480	EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment ↗	Naga Sai Abhiram kusumba et al.		NeurIPSSpotlight2025
481	Boundary-Value PDEs Meet Higher-Order Differential Topology-aware GNNs ↗	Yunfeng Liao et al.		NeurIPSSpotlight2025
482	4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos ↗	Zhen Xu et al.		NeurIPSSpotlight2025
483	Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning ↗	Yinjie Wang et al.		NeurIPSSpotlight2025
484	How many measurements are enough? Bayesian recovery in inverse problems with general distributions ↗	Ben Adcock et al. Ben Adcock, Nick Huang		NeurIPSSpotlight2025
485	Diffusion Generative Modeling on Lie Group Representations ↗	Marco Bertolini et al.		NeurIPSSpotlight2025
486	EGGS: Exchangeable 2D/3D Gaussian Splatting for Geometry-Appearance Balanced Novel View Synthesis ↗	Yancheng Zhang et al.		NeurIPSSpotlight2025
487	CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models ↗	Shristi Das Biswas et al.		NeurIPSSpotlight2025
488	Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs ↗	XiangCheng Zhang et al.		NeurIPSSpotlight2025
489	Low-degree evidence for computational transition of recovery rate in stochastic block model ↗	Jingqiu Ding et al.		NeurIPSSpotlight2025
490	Nonlinear Laplacians: Tunable principal component analysis under directional prior information ↗	Yuxin Ma et al. Yuxin Ma, Dmitriy Kunisky		NeurIPSSpotlight2025
491	Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment ↗	Bryan Sangwoo Kim et al.		NeurIPSSpotlight2025
492	Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning ↗	Yibo Zhao et al.		NeurIPSSpotlight2025
493	What are you sinking? A geometric approach on attention sink ↗	Valeria Ruscio et al.		NeurIPSSpotlight2025
494	KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment ↗	Yuxing Lu et al.		NeurIPSSpotlight2025
495	MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems ↗	Xuanming Zhang et al.		NeurIPSSpotlight2025
496	Enhancing CLIP Robustness via Cross-Modality Alignment ↗	Xingyu Zhu et al.		NeurIPSSpotlight2025
497	Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality ↗	Mincheol Park et al.		NeurIPSSpotlight2025
498	On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization ↗	Shaocong Ma et al. Shaocong Ma, Heng Huang		NeurIPSSpotlight2025
499	Gradient Variance Reveals Failure Modes in Flow-Based Generative Models ↗	Teodora Reu et al.		NeurIPSSpotlight2025
500	TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception ↗	Runjian Chen et al.		NeurIPSSpotlight2025
501	Boosting Generative Image Modeling via Joint Image-Feature Synthesis ↗	Theodoros Kouzelis et al.		NeurIPSSpotlight2025
502	A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone ↗	Jitai Hao et al.		NeurIPSSpotlight2025
503	SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering ↗	Ruimeng Liu et al.		NeurIPSSpotlight2025
504	Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification ↗	Zhongao Zhou et al.		NeurIPSSpotlight2025
505	MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference ↗	Haibo Tong et al.		NeurIPSSpotlight2025
506	Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set ↗	Chenghao Liu et al.		NeurIPSSpotlight2025
507	Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search ↗	Yuichi Inoue et al.		NeurIPSSpotlight2025
508	RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving ↗	Huacan Wang et al.		NeurIPSSpotlight2025
509	Hierarchical Shortest-Path Graph Kernel Network ↗	Jiaxin Wang et al.		NeurIPSSpotlight2025
510	Differential Privacy on Fully Dynamic Streams ↗	Yuan Qiu et al. Yuan Qiu, Ke Yi		NeurIPSSpotlight2025
511	Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More ↗	Jinwoo Lim et al.		NeurIPSSpotlight2025
512	SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications ↗	Gabriele Oliaro et al.		NeurIPSSpotlight2025
513	Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference ↗	Weizhi Fei et al.		NeurIPSSpotlight2025
514	UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting ↗	Kai He et al.		NeurIPSSpotlight2025
515	When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs ↗	Xiaomin Li et al.		NeurIPSSpotlight2025
516	On Agnostic PAC Learning in the Small Error Regime ↗	Julian Asilis et al.		NeurIPSSpotlight2025
517	Wavelet Canonical Coherence for Nonstationary Signals ↗	Haibo Wu et al.		NeurIPSSpotlight2025
518	Language Modeling by Language Models ↗	Junyan Cheng et al.		NeurIPSSpotlight2025
519	Plasticity as the Mirror of Empowerment ↗	David Abel et al.		NeurIPSSpotlight2025
520	PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts ↗	Zeman Li et al.		NeurIPSSpotlight2025
521	Language Models can Self-Improve at State-Value Estimation for Better Search ↗	Ethan Mendes et al. Ethan Mendes, Alan Ritter		NeurIPSSpotlight2025
522	Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity ↗	Jun Wang et al.		NeurIPSSpotlight2025
523	Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare ↗	Kira Goldner et al. Kira Goldner, Taylor Lundy		NeurIPSSpotlight2025
524	Decomposing stimulus-specific sensory neural information via diffusion models ↗	Steeve Laquitaine et al.		NeurIPSSpotlight2025
525	Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses ↗	Han Bao et al.		NeurIPSSpotlight2025
526	Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation ↗	Toshinori Kitamura et al.		NeurIPSSpotlight2025
527	To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL ↗	Yuda Song et al.		NeurIPSSpotlight2025
528	A learnability analysis on neuro-symbolic learning ↗	Hao-Yuan He et al. Hao-Yuan He, Ming Li		NeurIPSSpotlight2025
529	Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection ↗	Jinyu Cai et al.		NeurIPSSpotlight2025
530	Restoring Pruned Large Language Models via Lost Component Compensation ↗	Zijian Feng et al.		NeurIPSSpotlight2025
531	Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models ↗	Xiaowen Cai et al.		NeurIPSSpotlight2025
532	GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving ↗	Shuai Liu et al.		NeurIPSSpotlight2025
533	SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment ↗	Qi Xu et al.		NeurIPSSpotlight2025
534	HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning ↗	Guancheng Wan et al.		NeurIPSSpotlight2025
535	Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language Modeling ↗	Wentao Lu et al.		NeurIPSSpotlight2025
536	Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding ↗	Yiming Wang et al.		NeurIPSSpotlight2025
537	PoE-World: Compositional World Modeling with Products of Programmatic Experts ↗	Wasu Top Piriyakulkij et al.		NeurIPSSpotlight2025
538	Uni-LoRA: One Vector is All You Need ↗	Kaiyang Li et al.		NeurIPSSpotlight2025
539	Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding ↗	Hanyin Wang et al.		NeurIPSSpotlight2025
540	Stochastic Process Learning via Operator Flow Matching ↗	Yaozhong Shi et al.		NeurIPSSpotlight2025
541	Strategic Costs of Perceived Bias in Fair Selection ↗	L. Elisa Celis et al.		NeurIPSSpotlight2025
542	A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective ↗	Lianghe Shi et al.		NeurIPSSpotlight2025
543	AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders ↗	Yuezhou Hu et al.		NeurIPSSpotlight2025
544	Depth-Width Tradeoffs for Transformers on Graph Tasks ↗	Gilad Yehudai et al.		NeurIPSSpotlight2025
545	Refinement Methods for Distributed Distribution Estimation under $\ell^p$-Losses ↗	Deheng Yuan et al.		NeurIPSSpotlight2025
546	Measuring and Guiding Monosemanticity ↗	Ruben Härle et al.		NeurIPSSpotlight2025
547	Variational Transdimensional Inference ↗	Laurence Davies et al.		NeurIPSSpotlight2025
548	Scaling Laws For Scalable Oversight ↗	Joshua Engels et al.		NeurIPSSpotlight2025
549	A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization ↗	Hongxu Chen et al.		NeurIPSSpotlight2025
550	Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting ↗	Wei Chen et al. Wei Chen, Yuxuan Liang		NeurIPSSpotlight2025
551	FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion ↗	Akide Liu et al.		NeurIPSSpotlight2025
552	Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition ↗	Jongseo Lee et al.		NeurIPSSpotlight2025
553	Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection ↗	Shuhai Zhang et al.		NeurIPSSpotlight2025
554	Robust Graph Condensation via Classification Complexity Mitigation ↗	Jiayi Luo et al.		NeurIPSSpotlight2025
555	CausalPFN: Amortized Causal Effect Estimation via In-Context Learning ↗	Vahid Balazadeh et al.		NeurIPSSpotlight2025
556	High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction ↗	Seongsu Kim et al.		NeurIPSSpotlight2025
557	🎧MOSPA: Human Motion Generation Driven by Spatial Audio ↗	Shuyang Xu et al.		NeurIPSSpotlight2025
558	Absolute Zero: Reinforced Self-play Reasoning with Zero Data ↗	Andrew Zhao et al.		NeurIPSSpotlight2025
559	Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry ↗	Masanari Kimura		NeurIPSSpotlight2025
560	Vision Transformers Don't Need Trained Registers ↗	Nicholas Jiang et al.		NeurIPSSpotlight2025
561	Object-centric 3D Motion Field for Robot Learning from Human Videos ↗	Zhao-Heng Yin et al.		NeurIPSSpotlight2025
562	Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation ↗	Shuo Yang et al.		NeurIPSSpotlight2025
563	Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations ↗	Olawale Elijah Salaudeen et al.		NeurIPSSpotlight2025
564	Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning ↗	Emile Timothy Anand et al.		NeurIPSSpotlight2025
565	EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes ↗	Xiaoshan Wu et al.		NeurIPSSpotlight2025
566	LaViDa: A Large Diffusion Language Model for Multimodal Understanding ↗	Shufan Li et al.		NeurIPSSpotlight2025
567	Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning ↗	Quanjiang Li et al.		NeurIPSSpotlight2025
568	Scalable Fingerprinting of Large Language Models ↗	Anshul Nasery et al.		NeurIPSSpotlight2025
569	Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? ↗	Junchi Yu et al.		NeurIPSSpotlight2025
570	Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components ↗	Abel Jansma		NeurIPSSpotlight2025
571	Long-Tailed Recognition via Information-Preservable Two-Stage Learning ↗	Fudong Lin et al. Fudong Lin, Xu Yuan		NeurIPSSpotlight2025
572	Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures ↗	Shuqing Luo et al.		NeurIPSSpotlight2025
573	Data Mixing Can Induce Phase Transitions in Knowledge Acquisition ↗	Xinran Gu et al.		NeurIPSSpotlight2025
574	Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models ↗	Wenda Li et al. Wenda Li, Huijie Zhang, Qing Qu		NeurIPSSpotlight2025
575	Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies ↗	Runze Yan et al.		NeurIPSSpotlight2025
576	From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks ↗	Awa Khouna et al.		NeurIPSSpotlight2025
577	Repo2Run: Automated Building Executable Environment for Code Repository at Scale ↗	Ruida Hu et al.		NeurIPSSpotlight2025
578	Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery ↗	Ming Hu et al.		NeurIPSSpotlight2025
579	Unlocking Dataset Distillation with Diffusion Models ↗	Brian Bernhard Moser et al.		NeurIPSSpotlight2025
580	Vision-centric Token Compression in Large Language Model ↗	Ling Xing et al.		NeurIPSSpotlight2025
581	VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction ↗	Chaoyou Fu et al.		NeurIPSSpotlight2025
582	EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling ↗	Jia-Hua Lee et al.		NeurIPSSpotlight2025
583	UniTok: a Unified Tokenizer for Visual Generation and Understanding ↗	Chuofan Ma et al.		NeurIPSSpotlight2025
584	NormFit: A Lightweight Solution for Few-Shot Federated Learning with Non-IID Data ↗	Azadeh Motamedi et al.		NeurIPSSpotlight2025
585	Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs ↗	Insu Lee et al.		NeurIPSSpotlight2025
586	Accelerating Visual-Policy Learning through Parallel Differentiable Simulation ↗	Haoxiang You et al.		NeurIPSSpotlight2025
587	Online Prediction with Limited Selectivity ↗	Licheng Liu et al. Licheng Liu, Mingda Qiao		NeurIPSSpotlight2025
588	Generative Trajectory Stitching through Diffusion Composition ↗	Yunhao Luo et al.		NeurIPSSpotlight2025
589	VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs ↗	Shmuel Berman et al. Shmuel Berman, Jia Deng		NeurIPSSpotlight2025
590	Neighborhood Self-Dissimilarity Attention for Medical Image Segmentation ↗	Chen Junren et al.		NeurIPSSpotlight2025
591	Learning to Factorize Spatio-Temporal Foundation Models ↗	Siru Zhong et al.		NeurIPSSpotlight2025
592	Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals ↗	Qinsi Wang et al.		NeurIPSSpotlight2025
593	Generalizable Insights for Graph Transformers in Theory and Practice ↗	Timo Stoll et al.		NeurIPSSpotlight2025
594	Principled Data Augmentation for Learning to Solve Quadratic Programming Problems ↗	Chendi Qian et al. Chendi Qian, Christopher Morris		NeurIPSSpotlight2025
595	Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable ↗	Ruoxin Chen et al.		NeurIPSSpotlight2025
596	CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding ↗	Yuchen Zhou et al.		NeurIPSSpotlight2025
597	Flattening Hierarchies with Policy Bootstrapping ↗	John Luoyu Zhou et al. John Luoyu Zhou, Jonathan Kao		NeurIPSSpotlight2025
598	HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios ↗	Kunyu Peng et al.		NeurIPSSpotlight2025
599	Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts ↗	Benjamin Schiffer et al. Benjamin Schiffer, Mark Sellke		NeurIPSSpotlight2025
600	GeoRemover: Removing Objects and Their Causal Visual Artifacts ↗	Zixin Zhu et al.		NeurIPSSpotlight2025
601	The Primacy of Magnitude in Low-Rank Adaptation ↗	Zicheng Zhang et al.		NeurIPSSpotlight2025
602	GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals ↗	Jiachen Lu et al.		NeurIPSSpotlight2025
603	Spatial Understanding from Videos: Structured Prompts Meet Simulation Data ↗	Haoyu Zhang et al.		NeurIPSSpotlight2025
604	SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning ↗	Huanyu Liu et al.		NeurIPSSpotlight2025
605	JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation ↗	Kai Liu et al.		NeurIPSSpotlight2025
606	Dimension-adapted Momentum Outscales SGD ↗	Damien Ferbach et al.		NeurIPSSpotlight2025
607	From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots ↗	Yuxuan Wang et al.		NeurIPSSpotlight2025
608	LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers ↗	Yusuf Dalva et al.		NeurIPSSpotlight2025
609	GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction ↗	Jiahe Li et al.		NeurIPSSpotlight2025
610	Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning ↗	Jiaru Zou et al.		NeurIPSSpotlight2025
611	scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration ↗	Jianle Sun et al.		NeurIPSSpotlight2025
612	Imitation Beyond Expectation Using Pluralistic Stochastic Dominance ↗	Ali Farajzadeh et al.		NeurIPSSpotlight2025
613	Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution ↗	Jacob Lin et al.		NeurIPSSpotlight2025
614	CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering ↗	Zhengqing Wang et al.		NeurIPSSpotlight2025
615	Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning ↗	Yixiu Mao et al.		NeurIPSSpotlight2025
616	To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning ↗	Ming Li et al.		NeurIPSSpotlight2025
617	DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy ↗	Yuran Wang et al.		NeurIPSSpotlight2025
618	STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation ↗	Hossein Goli et al.		NeurIPSSpotlight2025
619	Neural Atlas Graphs for Dynamic Scene Decomposition and Editing ↗	Jan Philipp Schneider et al.		NeurIPSSpotlight2025
620	LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation ↗	Huanlin Gao et al.		NeurIPSSpotlight2025
621	Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models ↗	Junhao Dong et al.		NeurIPSSpotlight2025
622	Thought Communication in Multiagent Collaboration ↗	Yujia Zheng et al.		NeurIPSSpotlight2025
623	Polyline Path Masked Attention for Vision Transformer ↗	Zhongchen Zhao et al.		NeurIPSSpotlight2025
624	PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models ↗	Tonglong Wei et al.		NeurIPSSpotlight2025
625	Optimization Inspired Few-Shot Adaptation for Large Language Models ↗	Boyan Gao et al.		NeurIPSSpotlight2025
626	Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging ↗	Hongjin Qian et al. Hongjin Qian, Zheng Liu		NeurIPSSpotlight2025
627	Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation ↗	Yuyang Li et al.		NeurIPSSpotlight2025
628	Toward Relative Positional Encoding in Spiking Transformers ↗	Changze Lv et al.		NeurIPSSpotlight2025
629	TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup ↗	Fanxu Meng et al.		NeurIPSSpotlight2025
630	Towards Understanding the Mechanisms of Classifier-Free Guidance ↗	Xiang Li et al. Xiang Li, Rongrong Wang, Qing Qu		NeurIPSSpotlight2025
631	PhysX-3D: Physical-Grounded 3D Asset Generation ↗	Ziang Cao et al.		NeurIPSSpotlight2025
632	Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study ↗	Guanlin Wu et al.		NeurIPSSpotlight2025
633	StreamForest: Efficient Online Video Understanding with Persistent Event Memory ↗	Xiangyu Zeng et al.		NeurIPSSpotlight2025
634	Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2 ↗	Ziqi Zhou et al.		NeurIPSSpotlight2025
635	Improving Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias ↗	Xinyan Liang et al.		NeurIPSSpotlight2025
636	Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization ↗	Qingyang Zhang et al.		NeurIPSSpotlight2025
637	MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification ↗	Yingying Feng et al.		NeurIPSSpotlight2025
638	RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness ↗	Fanhu Zeng et al.		NeurIPSSpotlight2025
639	Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation ↗	Hao Zhang et al.		NeurIPSSpotlight2025
640	OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects ↗	Mark He Huang et al.		NeurIPSSpotlight2025
641	Rectified Point Flow: Generic Point Cloud Pose Estimation ↗	TAO SUN et al.		NeurIPSSpotlight2025
642	Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation ↗	Xiang Li et al.		NeurIPSSpotlight2025
643	SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation ↗	Zhenyuan Qin et al.		NeurIPSSpotlight2025
644	StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold ↗	Zhizhong Li et al.		NeurIPSSpotlight2025
645	Non-Clairvoyant Scheduling with Progress Bars ↗	Ziyad Benomar et al.		NeurIPSSpotlight2025
646	Jacobian-Based Interpretation of Nonlinear Neural Encoding Model ↗	Xiaohui Gao et al.		NeurIPSSpotlight2025
647	Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning ↗	Jian Liu et al.		NeurIPSSpotlight2025
648	VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank ↗	Tianhe Wu et al.		NeurIPSSpotlight2025
649	GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation ↗	Yi Dong et al.		NeurIPSSpotlight2025
650	G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems ↗	Guibin Zhang et al.		NeurIPSSpotlight2025
651	FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving ↗	Shuang Zeng et al.		NeurIPSSpotlight2025
652	E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products ↗	Yunyang Li et al.		NeurIPSSpotlight2025
653	Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler ↗	Zixuan Hu et al.		NeurIPSSpotlight2025
654	Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection ↗	Yu Guo et al.		NeurIPSSpotlight2025
655	AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping ↗	Haonan Dong et al.		NeurIPSSpotlight2025
656	Puppeteer: Rig and Animate Your 3D Models ↗	Chaoyue Song et al.		NeurIPSSpotlight2025
657	Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras ↗	Lingdong Kong et al.		NeurIPSSpotlight2025
658	DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing ↗	Chenxi Xie et al.		NeurIPSSpotlight2025
659	Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression ↗	Thibaut Loiseau et al.		NeurIPSSpotlight2025
660	DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling ↗	Yuang Ai et al.		NeurIPSSpotlight2025
661	Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective ↗	Xingjian Wu et al.		NeurIPSSpotlight2025
662	Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes ↗	Haonan Wang et al.		NeurIPSSpotlight2025
663	OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers ↗	Ziqiao Peng et al.		NeurIPSSpotlight2025
664	MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning ↗	Jinkun Hao et al.		NeurIPSSpotlight2025
665	Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion ↗	Xun Huang et al.		NeurIPSSpotlight2025
666	DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks ↗	Canyu Zhao et al.		NeurIPSSpotlight2025
667	Variational Learning Finds Flatter Solutions at the Edge of Stability ↗	Avrajit Ghosh et al.		NeurIPSSpotlight2025
668	Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization ↗	Yanhao Jia et al.		NeurIPSSpotlight2025
669	ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition ↗	Daolang Huang et al.		NeurIPSSpotlight2025
670	Fully Autonomous Neuromorphic Navigation and Dynamic Obstacle Avoidance ↗	Xiaochen Shang et al.		NeurIPSSpotlight2025
671	Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks ↗	Huanming Shen et al.		NeurIPSSpotlight2025
672	Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search ↗	Huanjin Yao et al.		NeurIPSSpotlight2025
673	ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search ↗	Mengdi Liu et al.		NeurIPSSpotlight2025
674	On the Value of Cross-Modal Misalignment in Multimodal Representation Learning ↗	Yichao Cai et al.		NeurIPSSpotlight2025
675	A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking ↗	Zixiang Zhao et al.		NeurIPSSpotlight2025
676	Multi-agent Markov Entanglement ↗	Shuze Chen et al. Shuze Chen, Tianyi Peng		NeurIPSSpotlight2025
677	SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving ↗	Haiming Zhang et al.		NeurIPSSpotlight2025
678	PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding ↗	Jang Hyun Cho et al.		NeurIPSSpotlight2025
679	Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? ↗	Hyeong Kyu Choi et al.		NeurIPSSpotlight2025
680	VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection ↗	Wuyang Li et al.		NeurIPSSpotlight2025
681	Approximate Domain Unlearning for Vision-Language Models ↗	Kodai Kawamura et al.		NeurIPSSpotlight2025
682	BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning ↗	Jianyang Gu et al.		NeurIPSSpotlight2025
683	GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments ↗	Enjun Du et al.		NeurIPSSpotlight2025
684	Q-Insight: Understanding Image Quality via Visual Reinforcement Learning ↗	Weiqi Li et al.		NeurIPSSpotlight2025
685	What Makes a Reward Model a Good Teacher? An Optimization Perspective ↗	Noam Razin et al.		NeurIPSSpotlight2025
686	$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models ↗	TaeHoon Yoon et al.		NeurIPSSpotlight2025
687	Do-PFN: In-Context Learning for Causal Effect Estimation ↗	Jake Robertson et al.		NeurIPSSpotlight2025
688	ReSim: Reliable World Simulation for Autonomous Driving ↗	Jiazhi Yang et al.		NeurIPSSpotlight2025
689	Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization ↗	Chris Kolb et al.		NeurIPSSpotlight2025