Zihan Wang
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge
- VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
- Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action