Boosting Generative Image Modeling via Joint Image-Feature Synthesis

NeurIPSSpotlight2025

Authors
Theodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

representation learning generative model image generation diffusion

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive