Jiaming Ji (吉嘉铭)

Phd Student at Peking University

Reinforcement Learning & Alignment
Large Language Models & Safety
World Model & Multimodal Large Language Models

Email: jiamg.ji at gmail dot com or jiamg.ji at stu.pku.edu.cn

[Google Scholar][GitHub]

I'm a PhD student at the Institute of Artificial Intelligence, Peking University, advised by Prof. Yaodong Yang (both a good teacher and a helpful friend in my life). During my tenure as a visiting scholar at the Hong Kong University of Science and Technology, I also had the privilege of being guided by Professor Yike Guo. My research journey began with Constrained Reinforcement Learning, with a focus on theoretical modeling, notably winning the NeurIPS 2022 MyoChallenge in robotic dexterous manipulation. My current work centers on advancing RL alignment, world models, and AI safety.

In 2025, I was honored to be named the Peking University Student of the Year, a distinction awarded to only 10 students across the university. Beyond this, my work has been distinguished by a series of fellowships, including the Tencent Project Up Scholarship (2026; one of 15 recipients nationwide), the Apple Scholar in AI/ML (2025, one of only 2 in Mainland China), and the Ant Group Intech Scholarship (2025; top 10 globally). Additionally, I was awarded the NSFC Grant for Young Doctoral Students (2023), standing as the sole recipient from the field of Intelligence Science at Peking University.

目前，我是北京大学人工智能研究院的博士生，导师为杨耀东教授（是我的导师，也是我人生中的朋友）。在香港科技大学访学期间，我也有幸得到郭毅可教授的指导。我的研究始于约束强化学习，专注于理论建模，并在机器人灵巧操作领域荣获NeurIPS 2022 MyoChallenge冠军。目前，我的工作聚焦于推进强化学习对齐、世界模型与 AI 安全。

2025 年，我荣获北京大学年度人物称号，全校仅10人获此殊荣。此外，我还先后获得腾讯青云奖学金（2026 年，全国15人）、苹果学者（2025 年，中国大陆仅2人）以及蚂蚁Intech奖学金（2025 年，全球前 10）。除此之外，我曾获得国家自然科学基金青年博士生专项资助（2023年北京大学智能科学领域唯一获批项目）和中国科协青年科技人才培育工程博士生专项计划（2025年）。