Please arrive early for registration before proceeding to the workshop venue. This is especially important for speakers and presenters scheduled early in the program.
Registration & Badge Pick-Up Schedule:
Physics-based models have been crucial for manipulation, enabling sim-to-real learning, model-predictive control, manipulation planning, and model-based design and verification. However, they typically require extensive manual effort and often fail to capture real-world complexity. Advances in generative modeling—particularly video models—offer a data-driven alternative but struggle with physical plausibility, consistency, and action conditioning. A promising direction is to integrate structured priors with scalable data-driven methods to improve dynamics prediction and generalization across diverse scenarios.
This workshop will explore relevant timely key topics, including state-action representations, supervision sources, generalizable inductive biases, the role of (generative) simulation and video models, and trade-offs in downstream planning, control, policy learning and evaluation.
We will bring together researchers from robotics, machine learning, and computer vision. The workshop targets audiences in manipulation, world modeling, reinforcement learning, and sim-to-real learning. Posters, panels, and live polls will foster debate and cross-level dialogue, allowing attendees to actively contribute to discussions.
8:00 - 8:05 | Opening Remarks |
8:05 - 8:25 | Paper Oral Presentations |
8:25 - 8:50 | Jerome Revaud: The *3R family: a Foundation Model for 3D vision |
8:50 - 9:15 | Katerina Fragkiadaki: From Explicit Physics Engines to Neural Simulators with Generative Models |
9:15 - 9:40 | Jonathan Tremblay: BUILDING BRIDGES, A KID’s DREAM |
9:40 - 10:05 | Chuang Gan: Virtual Community: A World Simulator for Humans, Robots, and Society |
10:05 - 10:30 | Yunzhu Li: Simulating and Manipulating Deformable Objects with Structured World Models |
10:30 - 11:30 | Coffee Break & Poster Sessions |
11:30 - 11:55 | Rares Ambrus: Structured Large Behavior Models for Dexterous Manipulation |
11:55 - 12:25 | Panel Discussion |
12:25 - 12:30 | Awards & Closing Remarks |
We cordially invite paper submissions relevant to the following (non-exhaustive) topics: