Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

ICLROral2026

Authors
Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak, David Held
Affiliation
Carnegie Mellon University
Venue
ICLR 2026
Track
Oral

TL;DR

a self-supervised object-centric world model that learns keypoints, and masks directly from videos, supports multi-modal conditioning, scaled to real-world multi-object datasets…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

self-supervised world model dataset video

← All ICLR 2026 Oral papers · Browse the whole archive