CVPR 2026PastEfficiencyComputer vision
1st Workshop on Video World Models: Interaction, Memory, Efficiency (Non-Proceedings Track)
CVPR 2026 Workshop VideoWorldModel
- Submission deadline
- May 3, 2026, 01:39 UTCOpenReview-synced 2026-05-03 01:39 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (24)
Fetched from OpenReview (v2) on 2026-06-10.
Building a Precise Video Language with Human–AI Oversight
Causal State Compression for Long-Horizon Video World Models: A Bounded-Drift Theory and Efficient Architecture
Causal State Entropy Bounds on Predictive Horizons in Video World Models
DECOMWM: Interpretable Reward Decomposition for World-Model-Based Trajectory Selection
Dexterous World Models
EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
Forecasting Motion in the Wild
Future Optical Flow Prediction Improves Robot Control & Video Generation
Inference-Time Planning with Action-Conditioned Video Models for Generalizable Robot Manipulation
Is Your Driving World Model an All-Around Player?
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
Olaf-World: Orienting Latent Actions for Video World Modeling
OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis
Rays as Pixels: Learning a Joint Distribution of Videos and Camera Trajectories
RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
SEGAR: Selective Enhancement for Generative Augmented Reality
Spectral World Models: Provably Consistent Long-Horizon Video Generation via Koopman Operator Decomposition
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics
VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control
Video Models Reason Early: Exploiting Plan Commitment for Maze Solving
WFM-Eval: Interpretable Error Diagnostics for Video World Models in Robotics
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation
WorldPack: Dynamic Frame Compression for Long-context Video World Modeling