OpenCodePapers

text-to-video-generation-on-videophy

Video GenerationText-to-Video Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodePCSAModelNameReleaseDate
PhysPO: Physics-Aware Local Preference Optimization for Physically Consistent Video Diffusion49.474.7PhysPO-CogVideoX (extra data)2026-09-08
PhysAlign: Learning Physical Priors for Dynamical Event-Driven Video Generation via Representation Alignment40.5453.98PhysAlign (extra data)2026-09-08
Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics37.947.5Phantom (Wan2.2-TI2V-5B)2026-04-09
DreamWorld: Unified World Modeling in Video Generation✓ Link26.252.9DreamWorld2026-02-28