I am a second-year PhD student, studying computer science at UC Santa Cruz, advised by Prof. Chenguang Wang. Previously, I earned a Bachelor of Engineering degree from the TsienHsueshen experimental class at Xidian University and a Master of Engineering degree in Signal and Information Systems from the University of Chinese Academy of Sciences. My CV is available here.

My research interests include LLM post-training and agentic AI.

Education

Ph.D, UC Santa Cruz (2025 - Present)
Baskin School of Engineering.

• Major: Computer Science
• Research Interests: LLM post-training and agentic AI.
• Advisor: Prof. Chenguang Wang

Ph.D, Washington University in St. Louis (2024 - 2025)
McKelvey School of Engineering.

• Major: Computer Science
• Research Interests: LLM post-training and agentic AI.
• Advisor: Prof. Chenguang Wang

Master, University of Chinese Academy of Sciences (2019 - 2022)
Aerospace Information Research Institute.

• Major: Signals and Information Processing
• Research Interests: Natural Language Processing, mainly in Information Extraction
• Advisor: Prof. Keming Chen

Bachelor, Xidian University (2015 - 2019)
School of Aerospace Science and Technology, TsienHsueshen experimental class.

• Major: Space Science and Technology

Publications

1. Y Potter, Z Wang, N Crispino, A Xiong, K Montgomery, F Pinto, E Chang, Y Chen, and C Christodoulopoulos, M Ziyadi, R Gupta, C Wang, B Li, D Song. VMDT: Decoding the Trustworthiness of Video Foundation Models. Neural Information Processing Systems, 2025. Paper
2. Ye Yuan, Junyu Luo, Guancheng Wan, Jinsheng Huang, Chengwu Liu, Junwei Yang, Yifang Qin, Zhiping Xiao, QingqingLong, Meng Xiao, Yiqiao Jin, Jianhong Tu, Yuqi Chen, Wei Ju, Zhongwei Wan, Yusheng Zhao, Xiao Luo, Yiwei Fu, Yizhou Sun, Wei Wang, Chenguang Wang, Ming Zhang. A Comprehensive Survey of Evaluating Multimodal Foundation Models: Hierarchical Perspective and Extensive Applications. Preprint, 2025.
3. K Montgomery, S Tan, Y Chen, S Zhuang, T Zhang, R Popa, and C Wang. Weak Discriminative Verification Enables Strong Test-time Scaling. Neural Information Processing Systems Workshop on Efficient Reasoning, 2025.
4. Yuqi Chen, Zequn Zhang, Guangyao Zhou, Xian Sun, Keming Chen. A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction[C].Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022: 4300-4309. Paper
5. Yuqi Chen, Keming Chen, Xian Sun, Zequn Zhang. Span-based dual-decoder framework for aspect sentiment triplet extraction[J]. Neurocomputing, 2022, 492: 211-221. Paper

Open Source Projects

rLLM, Reinforcement Learning for Language Agents. Key Contributor

• The project has earned 4,200 GitHub stars.
• GitHub: https://github.com/rllm-org/rllm

Works

Software Engineer Internship, Xizhi AI Education. (2022 - 2024)

• Scope: Visually Rich Document Information Extraction.

Xizhi AI Education is a company dedicated to the development of automated problem solving models, famous for developing the Eva Tutor App. I was responsible for extracting certain important information from the user’s questions to use as input for the solution model. After the emergence of LLMs, I was responsible for conducting experiments with prompt design and the local deployment of some small LLMs.