I am a postdoctoral research fellow at AI^2, Princeton AI Lab, working on the principled understanding of large language models and their application to engineering including design and control. I work closely with Prof. Mengdi Wang at Princeton.

Previously, I earned my Ph.D. in Computer Science from University of California, Los Angeles (UCLA), where I was advised by Prof. Quanquan Gu. Before that, I earned my Bachelor of Science from EECS at Peking University summa cum laude, where I was very fortunate to be advised by Prof. Liwei Wang.

My research interest covers various aspects of machine learning. Currently, I am particularly interested in applying insights from reinforcement learning and control theory to LLM training and inference, in the context of alignment and reasoning. You can find my curriculum vitae here.

🔥 News

• 2024.06-09: This summer, I had an internship at Meta Gen AI, where I worked on LLM alignment and reward modeling.
• 2024.05:  🎉🎉 2 papers accepted to ICML 2024.
• 2024.01:  🎉🎉 2 papers accepted to ICLR 2024.
• 2023.08:   It is my great honor to have been awarded the UCLA Dissertation Year Fellowship!
• 2023.07:  🎉🎉 1 paper accepted to ICML 2023, Hawaii.
• 2022.09:  🎉🎉 2 papers accepted to NeurIPS 2022, New Orleans.

📝 Publications & Preprints

• General Preference Modeling with Preference Representations for Aligning Language Models, preprint
  Yifan Zhang*, Ge Zhang*, Yue Wu*, Kangping Xu, Quanquan Gu

• Self-Play Preference Optimization for Language Model Alignment, preprint
  Yue Wu*, Zhiqing Sun*, Huizhuo Yuan*, Kaixuan Ji, Yiming Yang, Quanquan Gu

• Borda Regret Minimization for Generalized Linear Dueling Bandits, ICML 2024
  Yue Wu, Tao Jin, Qiwei Di, Hao Lou, Farzad Farnoud, Quanquan Gu

• Protein Conformation Generation via Force-Guided SE (3) Diffusion Models, ICML 2024
  Yan Wang, Lihao Wang, Yuning Shen, Yiqun Wang, Huizhuo Yuan, Yue Wu, Quanquan Gu

• Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits, ICLR 2024
  Qiwei Di, Tao Jin, Yue Wu, Heyang Zhao, Farzad Farnoud, Quanquan Gu

• DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text, ICLR 2024
  Xianjun Yang, Wei Cheng, Yue Wu, Linda Petzold, William Yang Wang, Haifeng Chen

• Personalized Federated Learning under Mixture of Distributions, ICML 2023
  Yue Wu, Shuaicheng Zhang, Wenchao Yu, Yanchi Liu, Quanquan Gu, Dawei Zhou, Haifeng Chen, Wei Cheng

• Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension, UAI 2023
  Yue Wu*, Jiafan He*, Quanquan Gu

• Active Ranking without Strong Stochastic Transitivity, NeurIPS 2022
  Hao Lou, Tao Jin, Yue Wu, Pan Xu, Quanquan Gu, Farzad Farnoud

• Towards Understanding the Mixture-of-Experts Layer in Deep Learning, NeurIPS 2022
  Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li

• Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons, AISTATS 2022
  Yue Wu*, Tao Jin*, Hao Lou, Pan Xu, Farzad Farnoud, Quanquan Gu

• Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation, AISTATS 2022
  Yue Wu, Dongruo Zhou, Quanquan Gu,

• A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods, NeurIPS 2020
  Yue Wu, Weitong Zhang, Pan Xu, Quanquan Gu,

• Towards Understanding the Spectral Bias of Deep Learning, IJCAI 2021
  Yuan Cao*, Zhiying Fang*, Yue Wu*, Dingxuan Zhou, Quanquan Gu

• To What Extent Do Different Neural Networks Learn the Same Representation: A Neuron Activation Subspace Match Approach, NeurIPS 2019 Spotlight
  Lunjia Hu, Jiayuan Gu, Yue Wu, Zhiqiang Hu, Liwei Wang

📖 Teaching

• 2021 Winter Teaching Assistant, UCLA CS161: Introduction to Artificial Intelligence
• 2022 Winter Teaching Assistant, UCLA CS161: Introduction to Artificial Intelligence

💬 Academic Service

• Reviewers of NeurIPS, ICML, ICLR, AISTATS, AAAI, IJCAI, and other conferences/journals in machine learning/data mining.
• Senior PC members of AAAI’23