About Me

I am a senior undergraduate in Artificial Intelligence (Class of ’26) at Yuanpei College, Peking University, majoring in Artificial Intelligence. I currently focus on Reinforcement Learning and Large Language Model (LLM), with a particular interest in designing learning algorithms 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?

I am currently at the Ant Research Reinforcement Learning Lab (Ant Group), supervised by Professor Yi Wu and Researcher Ligeng Zhu. Starting in 2026, I will begin my PhD at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University.

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 – Present
• 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 (supervisor: Prof. Yi Wu in Ant Group) June. 2025 - Present

Publications

• (Arxiv Preprint) Scaling Test-time Inference for Visual Grounding, 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).

• TVRA: Large Scale Tool-calling Vision Reasoning Agents

  Leading a research project on multimodal tool-calling agents for vision reasoning under the guidance from Prof. Yi Wu and Researcher Ligeng Zhu, with the goal of preparing the work for academic submission.

Language proficiency

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