Ziwei Liu
- 3EED: Ground Everything Everywhere in 3D
- Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
- GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
- GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
- Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity
- Imagine360: Immersive 360 Video Generation from Perspective Anchor
- PhysX-3D: Physical-Grounded 3D Asset Generation
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
- Video World Models with Long-term Spatial Memory
- VideoLucy: Deep Memory Backtracking for Long Video Understanding