Chuang Gan
- LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
- Learning 3D Persistent Embodied World Models
- MindJourney: Test-Time Scaling with World Models for Spatial Reasoning
- RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
- TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation
- Towards Understanding Camera Motions in Any Video