NeurIPS 2026 workshop proposal
Beyond pixels: understanding the physical world through geometry, characteristics, and multimodal sensing.
Physical World AI: Geometry, Characteristics, and Multimodal Sensing
PhysWorldAI is the proposed first workshop on physical world AI, centered on the question of how AI systems can perceive, represent, and reason about the physical world beyond appearance.
The final proposal organizes the program around three coupled pillars: physical geometry, physical characteristics, and physical sensors. It brings together computer vision, robotics, graphics, multimodal learning, haptics, audio, and physics-based simulation communities before benchmarks and protocols fragment across separate venues.
The requested format is a half-day workshop with moderated Q&A, contributed-paper spotlights, posters, live demos, and a synthesis panel across geometry, characteristics, sensing, and embodied AI.
Workshop format
Expected attendance
Poster capacity
Venue preferences
Geometry, characteristics, sensors, and cross-cutting physical AI
3D/4D reconstruction, articulated and deformable scene understanding, geometry-aware world models, and physically grounded view synthesis.
Material and physical property estimation, mass, friction, stiffness, elasticity, deformability, affordances, contact-rich interaction, differentiable simulation, and generative models of physical dynamics.
Multimodal sensing and fusion with tactile, force/torque, proprioceptive, RF, audio, depth, IMU, and event-based signals.
Embodied world models, robot manipulation, sim-to-real transfer, multimodal simulators, benchmarks, datasets, evaluation protocols, and responsible deployment.
Preliminary schedule from the final proposal
Geometry
Characteristics
Sensors
Cross-cutting
Submission timeline in the final proposal
Eight-organizer team listed in the final proposal
Questions, sponsorship, program committee interest, or proposal coordination.
