Xinyan Hu

Hi! I am a CS PhD student at UC Berkeley and a member of the Berkeley AI Research (BAIR) Lab, working on AI alignment and safety, advised by Jacob Steinhardt and Michael I. Jordan. I was also an Anthropic AI safety Fellow working on LLM agent security.

Before coming to Berkeley, I received my B.S. in CS at Peking University, where I was fortunate to work with Xiaotie Deng on algorithmic game theory, auction theory and online learning. I also had the pleasure of working with Zhiwei Steven Wu (CMU) and Aleksandrs Slivkins (MSR) on multi-armed bandits and aligning online learning algorithms with human incentives.

Selected Papers

(* denotes equal contribution; † equal advising; α-β denotes alphabetical ordering)

Agentic Backdoors via Pretraining Poisoning

Xinyan Hu*, Pingbang Hu*, Chloe Loughridge, Xuanli He, Nicholas Carlini, Matthew Jagielski, Javier Rando, Yiming Zhang

[arXiv]

ATLAS: Exploring Scalable Activation-Space Data Attribution

Linda Cai*, Xinyan Hu*, Alexander Pan*, Socrates Osorio, Pratyay Pandey, Michael I. Jordan, Jacob Steinhardt

Findings of the Association for Computational Linguistics: EMNLP 2026

Understanding In-context Learning of Addition via Activation Subspaces
Xinyan Hu, Kayo Yin, Michael I Jordan, Jacob Steinhardt*, Lijie Chen*
Conference on Language Modeling, COLM 2026
[arXiv]
Incentivizing High-Quality Content in Online Recommender Systems

Xinyan Hu*, Meena Jagadeesan*, Michael I. Jordan, Jacob Steinhardt

Symposium on the Foundations of Responsible Computing, FORC 2026 (🏆 Best Student Paper Award)

[arXiv]

Incentivizing Combinatorial Bandit Exploration

(α-β) Xinyan Hu, Dung Daniel Ngo, Aleksandrs Slivkins, Zhiwei Steven Wu

NeurIPS 2022

[arXiv]

Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions

(α-β) Xiaotie Deng, Xinyan Hu, Tao Lin, Weiqiang Zheng

The Web Conference (WWW) 2022

[arXiv]

Selected Awards & Fellowship

Anthropic AI Safety Research Fellow, 2025
Leo KoGuan scholarship, 2021
Yang Fuqing & Wang Yangyuan Academician Scholarship, 2020
Chinese Girls' Mathematical Olympiad (CGMO), Gold Medal, 2017

Miscellaneous

I love spending time outdoors, immersing myself in nature, and capturing the fleeting beauty of everyday life through photography. I also enjoy listening to music and playing a variety of sports. Novak Djokovic has been my idol and a source of inspiration since I was 11. On one unforgettable solo adventure, I was lucky enough to meet him, watch him practice and get his autograph!

Page updated

Google Sites

Report abuse