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

Deepak Pathak, David Held, Tal Daniel, Aviv Tamar, Dan Haramati, Carl Qi, Amir Zadeh, Chuan Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• taldatech/lpwm

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce Latent Particle World Model (LPWM), a self-supervised objectcentric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object masks directly from video data, enabling it to learn rich scene decompositions without supervision. Our architecture is trained end-to-end purely from videos and supports flexible conditioning on actions, language, and image goals. LPWM models stochastic particle dynamics via a novel latent action module and achieves state-of-the-art results on diverse real-world and synthetic datasets. Beyond stochastic video modeling, LPWM is readily applicable to decision-making, including goal-conditioned imitation learning, as we demonstrate in the paper. Code, data, pre-trained models and video rollouts are available: https://taldatech.github.io/lpwm-web

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.04553")
get_code_for_paper("2603.04553")
have("2603.04553")

Connect an agent — have() is free.