NeurIPS WORKSHOP
Robot Learning with World Models: Capabilities, Frontiers, and Challenges
December 11th or 12th, 2026
Sydney, Australia

This workshop explores using world models to advance Physical AI and address key challenges in robot learning, reasoning, and control. Recent breakthroughs in world modeling (e.g., Genie 3, Cosmos, Cosmos 3) have spurred significant progress in enabling robots to reason (e.g., Du et al. 2024, Physical Intelligence 2026), learn (e.g., Hafner et al. 2025), and be evaluated (e.g., Gemini Robotics Team 2025) in imagined scenarios. Furthermore, integrating spatiotemporal physical dynamics into control policies (World Action Models) has led to the emergence of zero-shot and visuomotor control policies (e.g., DreamZero, Cosmos Policy). However, state-of-the-art world models are primarily vision-focused and function essentially as controllable video generation models with plausible physical dynamics. The real world is far more complex, and fundamental challenges persist in consistency, physical accuracy, and the lack of multi-modalities for physical interactions. The goal of this workshop is to bring together researchers and practitioners working at the frontiers of developing Physical AI with world models. We aim to exchange ideas on the state-of-the-art of controllable video models and discuss the critical challenges the community faces in bridging the gap between simulated dynamics and real-world physical interactions.

Tentative Schedule

Location: TBD

Room Capacity: TBD

TimeEvent
8:50 - 9:00Opening Remarks
9:00 - 10:00Invited Talk 1 & 2
10:00 - 10:15Coffee Break
10:15 - 11:00Oral Presentations
11:00 - 12:00Invited Talk 3 & 4
12:00 - 13:00Lunch
13:00 - 14:00Poster Session 1
14:00 - 15:30Invited Talk 5, 6, 7
15:30 - 16:15Demo & Networking
16:15 - 16:30Coffee Break
16:30 - 17:15Panel Discussion
17:15 - 18:00Poster Session 2

All times are in Australian Eastern Standard Time (AEST).

Invited Speakers

Organizers

Call For Papers

We invite the submission of research papers, position papers, and demo proposals on the topic of world models for robot learning. This workshop focuses on the intersection of world models and robotics, exploring how predictive models of environment dynamics can advance Physical AI.

Topics of interest include, but are not limited to:

  • World Action Models (WAMs): Unifying world dynamics, spatiotemporal understanding, and robot action generation.
  • Learning, reasoning, and evaluation with imagined rollouts: Leveraging latent/observation space rollouts for planning, causal reasoning, and safety.
  • Multi-modality beyond vision: Integrating tactile sensing, proprioception, force feedback, audio, and other modalities.
  • Physical accuracy and spatiotemporal consistency: Simulating stable reality, realistic dynamics, and reliable control.
  • Evaluation metrics and benchmarks: Action-conditioned metrics and standardized benchmarks focusing on physical plausibility.

Submission Types:

  • Full Papers: Up to 8 pages in NeurIPS or ICLR format, with potentially large-scale experiments.
  • Short Papers: 2-4 pages in NeurIPS or ICLR format, with proof-of-concept demonstrations (demos, code, blog posts).
  • Proposals for demo and networking group: 1 page in NeurIPS or ICLR format, with a light-weight and casual form. The accepted proposals will have a space at the Demo and Networking session.

Important Dates (Tentative):

  • Submission Deadline: August 29, 2026, AoE
  • Author Notification: September 25, 2026, AoE
  • Camera Ready Deadline: November 30, 2026, AoE
  • Workshop Date: December 11 or 12, 2026 (TBD)

Accepted papers will be presented during poster sessions, with exceptional submissions selected for spotlight oral presentations.

All accepted papers will be made publicly available as non-archival reports, allowing for future submissions to archival conferences or journals.

Please submit your papers to the Open Review site. For demo and networking proposals, please submit 1 page PDF to the google form.

Camera Ready Instructions

Please incorporate reviewers’ feedback and prepare your camera-ready submission. Please submit your camera-ready version on OpenReview. Your camera-ready submission should be de-anonymized and include at most 8 pages for full papers, and 2-4 pages for short papers, excluding references and appendices. The paper format must follow the NeurIPS style template.

The camera-ready deadline is November 30, 2026, Anywhere on Earth (AoE).

This website is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License and is based on the Leela Interp project. That means you're free to borrow the source code of this website with attribution.