Similar Items: Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
- A Benchmark for Interactive World Models with a Unified Action Generation Framework
- 3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark
- Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movements
- CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
- Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
- PhyGround: Benchmarking Physical Reasoning in Generative World Models