Qihang Peng | 彭启航

I'm a first-year Ph.D. student at MMLab, The Chinese University of Hong Kong, advised by Prof. Hongsheng Li. My research interests currently center on multimodal pretraining, from architecture design to training dynamics to data analysis. I'm also interested in agentic learning, embodied intelligence, visual generation, and LLM reasoning.

I received my bachelor's degree from Xingjian College, Tsinghua University in 2026. During my undergraduate studies, I did research at LeapLab, Tsinghua University, advised by Prof. Gao Huang.

If you're interested in my research, feel free to reach out, I'm always open to discussion and potential collaborations.

CV  /  Google Scholar  /  Github  /  Twitter

WeChat: qihang_peng    Email: pengqihang22@gmail.com

Selected Publications

*Equal contribution

A generalist robotic manipulation foundation model that aligns representations, motions, and behaviors across 15 robot platforms. Trained on ~38,100 hours of pre-training data. Ranks first on RoboChallenge and surpasses π0.5 across 6 OOD benchmarks.

A unified navigation model built on Qwen3-VL spanning 5 task families with 15.6M training samples. Achieves SOTA on VLN-CE RxR, HM3Dv2, EVT-Bench, and NAVSIM with real-world deployment on Unitree Go2 quadruped robot.

A language-conditioned video world model with dual-stream MMDiT and MLLM action encoding, trained on 8.6M video-text pairs across 20+ robot morphologies. Ranks #1 on EWMBench, DreamGen Bench, and leads open-source models on WorldModelBench and PBench.

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