Mei, Song

39 publications

NeurIPS 2025 A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics Licong Lin, Song Mei

NeurIPS 2025 Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers Yixiao Huang, Hanlin Zhu, Tianyu Guo, Jiantao Jiao, Somayeh Sojoudi, Michael I. Jordan, Stuart Russell, Song Mei

ICML 2025 Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks Yuhang Cai, Kangjie Zhou, Jingfeng Wu, Song Mei, Michael Lindsey, Peter Bartlett

ICML 2025 Improving LLM Safety Alignment with Dual-Objective Optimization Xuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song

NeurIPS 2025 OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models Ziheng Cheng, Yixiao Huang, Hui Xu, Somayeh Sojoudi, Xuandong Zhao, Dawn Song, Song Mei

NeurIPS 2025 Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

ICLR 2025 U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models Song Mei

NeurIPSW 2024 Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs Tianyu Guo, Druv Pai, Yu Bai, Jiantao Jiao, Michael Jordan, Song Mei

NeurIPSW 2024 Choose Your Anchor Wisely: Effective Unlearning Diffusion Models via Concept Reconditioning Jingyu Zhu, Ruiqi Zhang, Licong Lin, Song Mei

ICLR 2024 How Do Transformers Learn In-Context Beyond Simple Functions? a Case Study on Learning with Representations Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai

NeurIPS 2024 Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization Yuhang Cai, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett

NeurIPSW 2024 Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

NeurIPS 2024 Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm Leo Zhou, Joao Basso, Song Mei

ICLR 2024 Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining Licong Lin, Yu Bai, Song Mei

NeurIPSW 2023 Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models Song Mei, Yuchen Wu

NeurIPSW 2023 How Do Transformers Learn In-Context Beyond Simple Functions? a Case Study on Learning with Representations Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai

ICML 2023 Lower Bounds for Learning in Revealing POMDPs Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai

ICLR 2023 Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms Fan Chen, Yu Bai, Song Mei

NeurIPSW 2023 Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining Licong Lin, Yu Bai, Song Mei

NeurIPSW 2023 Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining Licong Lin, Yu Bai, Song Mei

NeurIPS 2023 Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection Yu Bai, Fan Chen, Huan Wang, Caiming Xiong, Song Mei

ICMLW 2023 Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection Yu Bai, Fan Chen, Huan Wang, Caiming Xiong, Song Mei

NeurIPS 2023 What Can a Single Attention Layer Learn? a Study Through the Random Features Lens Hengyu Fu, Tianyu Guo, Yu Bai, Song Mei

NeurIPS 2022 Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu

ICLR 2022 Efficient and Differentiable Conformal Prediction with General Function Classes Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong

NeurIPS 2022 Learning with Convolution and Pooling Operations in Kernel Methods Theodor Misiakiewicz, Song Mei

ICML 2022 Near-Optimal Learning of Extensive-Form Games with Imperfect Information Yu Bai, Chi Jin, Song Mei, Tiancheng Yu

ICLRW 2022 Near-Optimal Learning of Extensive-Form Games with Imperfect Information Yu Bai, Chi Jin, Song Mei, Tiancheng Yu

NeurIPS 2022 Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games Ziang Song, Song Mei, Yu Bai

ICLR 2022 The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods Nikhil Ghosh, Song Mei, Bin Yu

ICLR 2022 When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? Ziang Song, Song Mei, Yu Bai

ICML 2021 Don’t Just Blame Over-Parametrization for Over-Confidence: Theoretical Analysis of Calibration in Binary Classification Yu Bai, Song Mei, Huan Wang, Caiming Xiong

ICML 2021 Exact Gap Between Generalization Error and Uniform Convergence in Random Feature Models Zitong Yang, Yu Bai, Song Mei

COLT 2021 Learning with Invariances in Random Features and Kernel Models Song Mei, Theodor Misiakiewicz, Andrea Montanari

NeurIPS 2021 Understanding the Under-Coverage Bias in Uncertainty Estimation Yu Bai, Song Mei, Huan Wang, Caiming Xiong

NeurIPS 2020 When Do Neural Networks Outperform Kernel Methods? Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari

NeurIPS 2019 Limitations of Lazy Training of Two-Layers Neural Network Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari

COLT 2019 Mean-Field Theory of Two-Layers Neural Networks: Dimension-Free Bounds and Kernel Limit Song Mei, Theodor Misiakiewicz, Andrea Montanari

COLT 2017 Solving SDPs for Synchronization and MaxCut Problems via the Grothendieck Inequality Song Mei, Theodor Misiakiewicz, Andrea Montanari, Roberto Imbuzeiro Oliveira