|
Qingfeng He 何青峰 I am a first-year Ph.D. student in the Dept. of Automation at Tsinghua University, starting from Fall 2025. Prior to this, I obtained B.Eng. in Computer Science at Tsinghua University in 2025. My research focuses on Infrastructure for large-scale model training, Multimodal Large Models, and Reinforcement Learning (post-training and agentic RL for LLMs). I am a core contributor to ForgeTrain (OpenBMB), an open framework for training large models. If you are interested in my work, please feel free to contact me to discuss related topics or potential collaborations. |
Beijing, China |
News
• Apr 2026: One paper accepted by ACL 2026
(Response-G1, on proactive streaming video understanding). |
Selective Research Papers
Some representative papers are highlighted.
|
|
Survey
2026 |
Intelligent Remote Sensing Agents: A Survey
Jiaqi Tang*, Yingying Yan*, Qianzhou Wang*, Yuyang Xia*, Botong Geng*, Jianmin Chen*, Ke Ma, Youyang Zhai, Qingfeng He, Weigeng Shao, Yunjin Sun, Junwei Dai, Chuxi Chen, Xiaogang Xu, Kelu Yao, Lei Zhang, Wei Wei†, Qifeng Chen†, Antonio Plaza, Yanning Zhang Technical Report, 2026 paper / repository Curated collection of 100+ papers on intelligent remote sensing agents, with datasets, benchmarks, and application domains. |
|
ACL
2026 |
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Ke Ma*, Jiaqi Tang*, Bin Guo, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang, Qifeng Chen, Zhiwen Yu, Yunhao Liu Annual Meeting of the Association for Computational Linguistics (ACL), 2026 arXiv / code Explicit scene graph modeling for proactive streaming video understanding. |
Open Source• ForgeTrain (OpenBMB) — an open framework for training large models. I am a core contributor. |
| Template adapted from Jon Barron. |