NeurIPS 2026 workshop proposal

Workshop Proposal

Physical World AI: Geometry, Characteristics, and Multimodal Sensing

Proposal Summary

Final proposal details reflected from the PDF

Acronym: PhysWorldAI

Name: Physical World AI: Geometry, Characteristics, and Multimodal Sensing

Modern computer vision and embodied AI systems must act in the physical world, not merely describe it. The workshop frames physical world understanding around geometry, physical characteristics, and multimodal sensing, connecting vision, robotics, graphics, haptics, audio, and physics-based simulation.

Edition1st
FormatHalf day
Expected attendance200-300 attendees
Venue preferencesAtlanta, Paris, Sydney
Special requestsStreaming and recording
Poster boards20 poster boards

Call for Papers

Submission, review, and publication policy

  • Submission format: Long papers up to 8 pages and extended abstracts up to 4 pages, in NeurIPS 2026 style.
  • Review process: Double-blind review via OpenReview with at least 3 reviewers per paper.
  • Archival status: Non-archival; accepted papers are posted on the workshop website.
  • Dual submission: Concurrent submission to NeurIPS 2026 or other peer-reviewed venues is permitted if authors comply with those venues' policies.
  • Ethics statement: Submissions should address privacy in non-RGB sensing, safety in contact-rich interaction, and misuse risks of generative dynamics models.
Submission deadline August 29, 2026
Notification September 26, 2026
Camera-ready October 26, 2026

Topics of Interest

From structure to material properties and non-RGB sensing

Physical Geometry

3D/4D reconstruction, articulated and deformable scene understanding, geometry-aware world models, and physically grounded view synthesis.

Physical Characteristics

Material and physical property estimation, mass, friction, stiffness, elasticity, deformability, affordances, contact-rich interaction, differentiable simulation, and generative models of physical dynamics.

Physical Sensors

Multimodal sensing and fusion with tactile, force/torque, proprioceptive, RF, audio, depth, IMU, and event-based signals.

Cross-cutting

Embodied world models, robot manipulation, sim-to-real transfer, multimodal simulators, benchmarks, datasets, evaluation protocols, and responsible deployment.

Awards and Support

Sponsor commitments listed in the proposal

CyberBrain and 2077AI are listed as confirmed sponsors. The proposal names an Overall Best Paper Award and a Best Student Paper Award, with support also planned for student travel grants for underrepresented attendees and on-site logistics.