Tag
The project lets users prompt AI agents to play 1v1 football in a physics-based simulation, evaluating how well prompts translate to actions in embodied environments.
This paper presents a closed-loop framework combining physics-grounded reflection simulation, a diffusion-based video dereflection model (S2R-Removal), and a new benchmark (S2R-Bench), achieving state-of-the-art video reflection removal with fast inference.