I am a Member of Technical Staff at Physion Labs, working on distributed training systems, large-scale foundation models, and efficient AI infrastructure. I received my M.S. in Computer Science and Engineering from the University of Notre Dame.
My research interests include accelerated computing, distributed and memory-efficient training, large language models, multimodal learning, and scalable AI systems. I am the creator of MegaTrain, a system that enables full-precision training of models with more than 100 billion parameters on a single GPU. I have also contributed to projects including TinyGPT-V and Mora. My open-source projects have received more than 4,000 GitHub stars.
I am always open to research and open-source collaboration. Please feel free to contact me.
🔥 News
- 2026.02: 🚀 Achieved full-precision training of a 120B-parameter model on a single GPU, significantly improving efficiency over existing systems (e.g., DeepSpeed ZeRO-3).
- 2026.01: 🎉 Our Paper BLURR Accpeted by WWW 2026 Demo Track! Congratulations to my intern!
- 2025.09: 🎉 Our Paper Accpeted by NeurIPS 2025
- 2025.08: 🎉 Our Paper Accpeted by CoLM 2025
- 2024.03: 🎉 Mora: Enabling Generalist Video Generation via A Multi-Agent Framework is preprint.
- 2024.02: 🎉 Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models is preprint.
- 2024.02: 🎉 I will be attending the University of Notre Dame in August 2024 and pursuing a PhD under the guidance of Prof. Yanfang Ye.
- 2023.12: 🎉 TinyGPT-V is preprint.
- 2023.05: 🎉 Our paper RPN was accepted by 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2023).
- 2023.05: 🔥 We release ArtGPT-4
📝 Selected Publications (❁Equal contributions)
- MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU, Zhengqing Yuan, Hanchi Sun, Lichao Sun, Yanfang Ye (Accepted by CoLM 26)
- [DepthSSD: Rethinking Residual Connections via State Space Models on the Depth Axis], Zhengqing Yuan, Xiaoyu Ma, Yunhong He, Zhengtao Yao, Lichao Sun, Yanfang Ye (Accepted by CoLM 26)
- BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Model, Xiaoyu Ma❁, Zhengqing Yuan❁, Zheyuan Zhang, Kaiwen Shi, Lichao Sun, Yanfang Ye (WWW 26 Demo Track)
- Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-Recursions, Yunhong He❁, Zhengqing Yuan❁, Weixiang Sun, Yiyang Li, Yixin Liu, Yanfang Ye, Lichao Sun (AAAI 26)
- 3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation, Yunhong He❁, Zhengqing Yuan❁, Zhengzhong Tu, Yanfang Ye, Lichao Sun (AAAI 26 Demo Track)
- ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions, Yue Huang, Zhengzhe Jiang, Xiaonan Luo, Kehan Guo, Haomin Zhuang, Yujun Zhou, Zhengqing Yuan, Xiaoqi Sun, Jules Schleinitz, Yanbo Wang, Shuhao Zhang, Mihir Surve, Nitesh V Chawla, Olaf Wiest, Xiangliang Zhang (NeurIPS 25)
- Exposing and Patching the Flaws of Large Language Models in Social Character Simulation, Yue Huang❁, Zhengqing Yuan❁, Yujun Zhou❁, Kehan Guo, Xiangqi Wang, Haomin Zhuang, Weixiang Sun, Lichao Sun, Jindong Wang, Yanfang Ye, Xiangliang Zhang (CoLM 25)
- Mora: Enabling Generalist Video Generation via A Multi-Agent Framework, Zhengqing Yuan, Yixin Liu, Yihan Cao, Weixiang Sun, Haolong Jia, Ruoxi Chen, Zhaoxu Li, Bin Lin, Li Yuan, Lifang He, Chi Wang, Yanfang Ye, Lichao Sun (Github 1.6k+ Stars)
- Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models, Yixin Liu❁, Kai Zhang❁, Yuan Li❁, Zhiling Yan❁, Chujie Gao❁, Ruoxi Chen❁, Zhengqing Yuan❁, Yue Huang❁, Hanchi Sun❁, Jianfeng Gao, Lifang He, Lichao Sun
- TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones, Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, Lichao Sun (Github 1.3k+ Stars)
📰 Peer Review
- ICML 2026 Reviwer
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- IEEE Latin America Transaction Reviwer
- COLM 2025 Reviwer
- ACM KDD 2025 Reviwer
- IEEE Transactions on Medical Imaging Reviwer
- IEEE Access Reviewer
- AAAI 2026 Reviwer
- ICLR 2026 Reviwer
🎖 Honors and Awards
- 2021.10 National Inspirational Scholarship
- 2021.10 University of Third Class Scholarship
- 2022.10 Provincial Student Entrepreneurship Project
- 2022.10 University of Three Good Students
- 2023.04 Top Ten Students of Anhui Polytechnic University
- 2026.02 ICML Sliver Reviwer
📖 Educations
- 2024.08 - 2029.05, PhD Candicate, University of Notre Dame.
- 2020.09 - 2024.06, Undergraduate, Shool of Artificial Intelligence, Anhui Polytechnic University Wuhu.
📖 Presentation
- 2023.08, AI TIMES (Tsinghua University), ArtGPT-4
🧢 Membership
- 2022.12 - 2023.12, IEEE Student Member
- 2024.02 - 2025.02, IEEE Student Member
- 2025.02 - 2026.02, IEEE Member
💻 Internships
- 2024.9 - 2025.4, Research Intern at US Lab, Mohamed bin Zayed University of Artificial Intelligence, US Lab.
- 2023.7 - 2024.8, Visiting student at LAIR Lab, Lehigh University, US. (Supervisor: Lichao Sun)
- 2023.10 - 2024.5, Research Intern at HAOMO.AI.
- 2021.11 - 2022.11, Intelligent Human-Computer Interaction Joint Laboratory, Wuhu. (Algorithm, Front-end and Back-end Engineers)