About Me

I am a first-year PhD student at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, supervised by Professor Wei Xu. I received my bachelor’s degree from Yuanpei College, Peking University, where I majored in Artificial Intelligence. I currently focus on Reinforcement Learning and Large Language Model (LLM), with a particular interest in agnetic workflow design and LLM post-training. My research interests also cover AI Alignment and Interpretability. My research is driven by the following questions:

How to close the gap between artificial intelligence and human-level intelligence by designing reliable AI system and efficient learning algorithm?

Honor and Awards

• Peking University Freshman Scholarship (2022)
• Dean’s Scholarship, Institute for Artificial Intelligence, Peking University (2025)

Experiences

• Tong Class, Peking University Undergraduate Student September. 2022 – 2026
• PAIR Lab: PKU Alignment and Interaction Research Lab Research Intern (advisor: Prof. Yaodong Yang at Institute for AI, Peking University) July. 2023 – February. 2025
• Tsinghua MARS Lab: Multimedia Computing, Autonomous Driving, Robotics and Sensors Visiting Student Researcher (advisor: Prof. Hang Zhao at IIIS, Tsinghua University) February. 2025 – June. 2025
• Ant Research Reinforcement Learning Lab Research Intern (advisor: Prof. Yi Wu) June. 2025 - June. 2026
• Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University PhD Student (advisor: Prof. Wei Xu) September. 2026 - Present

Publications

• (Arxiv Preprint) Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning Changye Li, Meng Lu, Yi Wu, Ligeng Zhu
• (ECCV 2026) EGM: Efficient Visual Grounding Language Models, Guanqi Zhan^*, Changye Li^*, Zhijian Liu, Yao Lu, Yi Wu, Song Han, Ligeng Zhu
• (Arxiv Preprint) Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback Derun Li^*, Changye Li^*, Yue Wang^*, Jianwei Ren, Xin Wen, Pengxiang Li, Leimeng Xu, Kun Zhan, Peng Jia, Xianpeng Lang, Ningyi Xu, Hang Zhao
• (ICML 2025 Poster) SAE-V: Interpreting Multimodal Models for Enhanced Alignment, Hantao Lou^*, Changye Li^*, Jiaming Ji, Yaodong Yang
• (ACL 2025 Best Paper) Language Models Resist Alignment: Evidence From Data Compression, Jiaming Ji^*, Kaile Wang^*, Tianyi Qiu^*, Boyuan Chen^*, Jiayi Zhou^*, Changye Li, Hantao Lou, Juntao Dai, Yunhuai Liu, Yaodong Yang
• (AAAI 2025) Towards efficient collaboration via graph modeling in reinforcement learning, Wenzhe Fan, Zishun Yu, Chengdong Ma, Changye Li, Yaodong Yang, Xinhua Zhang

Project

• AReaL: Ant Reasoning Reinforcement Learning for LLMs

  Contributed to building the training and inference code for Vision-Language Model (VLM).

Language proficiency

• Chinese: Native
• English: Advanced
• Hokkien: Intermediate
• Italiano, Español: Basic