physical plausibility
This term relates to the extent to which a model's predictions or outputs align with laws of physics or realistic behavior in the real world. In AI, particularly in areas such as robotics and simulations, ensuring physical plausibility is important to maintain credibility and reliability in applications.
- CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects
- FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation
- ForceFM: Enhancing Protein-Ligand Predictions through Force-Guided Flow Matching
- GeoVideo: Introducing Geometric Regularization into Video Generation Model
- HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
- I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
- OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback