Qihang Peng | 彭启航

I'm a senior undergraduate student at Xingjian College, Tsinghua University, and an incoming Ph.D. student at MMLab, CUHK. My research interests lie in Physical World Models and Embodied Foundation Models.

My research objective is to build an embodied system that can independently complete the understanding, planning, and world modeling of diverse scenes, and apply it to fields such as Robotics and Autonomous Driving.

Now I'm working closely with Prof. Gao Huang and Prof. Hongsheng Li. If you are also interested in this domain, please feel free to contact me.

CV  /  Google Scholar  /  Github  /  Twitter

WeChat: qihang_peng    Email: pengqihang22@gmail.com

Selected Publications

*Equal contribution

ColaVLA moves VLM reasoning into a compact latent space and decodes multi-scale causal trajectories in one pass. State-of-the-art in both open-loop and closed-loop settings with favorable efficiency and robustness on the nuScenes benchmark.

Make full use of multimodal information in ego-centric 3D visual grounding for point enhancement. State-of-the-art on the EmbodiedScan benchmark.

Use LLM and Ground Truth to enhance semantic details in prompt to reduce the ambiguity during training. Extract individual view semantics and enrich visual representation with global scene-level semantic.

Website Template