| 2025 | COLING | LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks. | Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham M. Kakade, Eran Malach, Samy Jelassi |
| 2025 | ICLR | Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems. | Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu |
| 2025 | ICLR | Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process. | Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu |
| 2025 | ICLR | Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2025 | ICLR | Physics of Language Models: Part 3.2, Knowledge Manipulation. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2025 | ICLR | Mixture of Parrots: Experts improve memorization more than reasoning. | Samy Jelassi, Clara Mohri, David Brandfonbrener, Alex Gu, Nikhil Vyas, Nikhil Anand, David Alvarez-Melis, Yuanzhi Li, Sham M. Kakade, Eran Malach |
| 2025 | ICLR | Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data. | Binghui Li, Yuanzhi Li |
| 2025 | ICML | On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics. | Binghui Li, Yuanzhi Li |
| 2025 | STOC | Provably Learning a Multi-head Attention Layer. | Sitan Chen, Yuanzhi Li |
| 2024 | AAAI | Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning. | Ruiqian Nai, Zixin Wen, Ji Li, Yuanzhi Li, Yang Gao |
| 2024 | ICLR | Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP. | Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu |
| 2024 | ICLR | Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs. | Aakash Lahoti, Stefani Karp, Ezra Winston, Aarti Singh, Yuanzhi Li |
| 2024 | ICLR | SmartPlay : A Benchmark for LLMs as Intelligent Agents. | Yue Wu, Xuan Tang, Tom M. Mitchell, Yuanzhi Li |
| 2024 | ICML | Physics of Language Models: Part 3.1, Knowledge Storage and Extraction. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2023 | COLT | Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2023 | COLT | The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks. | Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu |
| 2023 | ICLR | Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2023 | ICLR | Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2023 | ICLR | Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions. | Sitan Chen, Sinho Chewi, Jerry Li, Yuanzhi Li, Adil Salim, Anru Zhang |
| 2023 | ICLR | Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization. | Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu |
| 2023 | ICML | How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding. | Yuchen Li, Yuanzhi Li, Andrej Risteski |
| 2023 | ICML | Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality. | Dhruv Malik, Conor Igoe, Yuanzhi Li, Aarti Singh |
| 2023 | ICML | The Benefits of Mixup for Feature Learning. | Difan Zou, Yuan Cao, Yuanzhi Li, Quanquan Gu |
| 2023 | STOC | Learning Polynomial Transformations via Generalized Tensor Decompositions. | Sitan Chen, Jerry Li, Yuanzhi Li, Anru R. Zhang |
| 2022 | COLT | Complete Policy Regret Bounds for Tallying Bandits. | Dhruv Malik, Yuanzhi Li, Aarti Singh |
| 2022 | ICLR | Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs. | Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka |
| 2022 | ICLR | LoRA: Low-Rank Adaptation of Large Language Models. | Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen |
| 2022 | ICML | Towards understanding how momentum improves generalization in deep learning. | Samy Jelassi, Yuanzhi Li |
| 2022 | ICSE | Large-scale Security Measurements on the Android Firmware Ecosystem. | Qinsheng Hou, Wenrui Diao, Yanhao Wang, Xiaofeng Liu, Song Liu, Lingyun Ying, Shanqing Guo, Yuanzhi Li, Meining Nie, Haixin Duan |
| 2021 | COLT | A Law of Robustness for Two-Layers Neural Networks. | Sbastien Bubeck, Yuanzhi Li, Dheeraj M. Nagaraj |
| 2021 | FOCS | Feature Purification: How Adversarial Training Performs Robust Deep Learning. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2021 | FOCS | Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning. | Yuanzhi Li, Ruosong Wang, Lin F. Yang |
| 2021 | HPCC | A Highly Efficient Profiled Power Analysis Attack Based on Power Leakage Fitting. | Yuanzhi Li, Shanshan Xu, Yuling Luo, Sheng Qin, Shunsheng Zhang, Min Su |
| 2021 | ICAART | Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design. | Lei Li, Lei Wang, Yuanzhi Li, Jie Sheng |
| 2021 | ICLR | Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability. | Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar |
| 2021 | ICML | Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity. | Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan, Yuanzhi Li |
| 2021 | ICML | Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning. | Zixin Wen, Yuanzhi Li |
| 2021 | OSDI | PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. | Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, Zhihao Jia |
| 2021 | UAI | A heuristic for statistical seriation. | Komal Dhull, Jingyan Wang, Nihar B. Shah, Yuanzhi Li, R. Ravi |
| 2020 | COLT | Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without. | Sbastien Bubeck, Yuanzhi Li, Yuval Peres, Mark Sellke |
| 2020 | COLT | Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. | Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang |
| 2020 | SODA | Chasing Nested Convex Bodies Nearly Optimally. | Sbastien Bubeck, Bo'az Klartag, Yin Tat Lee, Yuanzhi Li, Mark Sellke |
| 2019 | COLT | Near-optimal method for highly smooth convex optimization. | Sbastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford |
| 2019 | COLT | Improved Path-length Regret Bounds for Bandits. | Sbastien Bubeck, Yuanzhi Li, Haipeng Luo, Chen-Yu Wei |
| 2019 | COLT | Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives. | Alexander V. Gasnikov, Pavel E. Dvurechensky, Eduard Gorbunov, Evgeniya A. Vorontsova, Daniil Selikhanovych, Csar A. Uribe, Bo Jiang, Haoyue Wang, Shuzhong Zhang, Sbastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford |
| 2019 | ICLR | Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees. | Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma |
| 2019 | ICML | A Convergence Theory for Deep Learning via Over-Parameterization. | Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song |
| 2019 | STOC | Competitively chasing convex bodies. | Sbastien Bubeck, Yin Tat Lee, Yuanzhi Li, Mark Sellke |
| 2018 | ALT | Sparsity, variance and curvature in multi-armed bandits. | Sbastien Bubeck, Michael B. Cohen, Yuanzhi Li |
| 2018 | COLT | Learning Mixtures of Linear Regressions with Nearly Optimal Complexity. | Yuanzhi Li, Yingyu Liang |
| 2018 | COLT | Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. | Yuanzhi Li, Tengyu Ma, Hongyang Zhang |
| 2018 | ICML | Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits. | Zeyuan Allen-Zhu, Sbastien Bubeck, Yuanzhi Li |
| 2018 | ICML | An Alternative View: When Does SGD Escape Local Minima? | Robert Kleinberg, Yuanzhi Li, Yang Yuan |
| 2018 | ICML | The Well-Tempered Lasso. | Yuanzhi Li, Yoram Singer |
| 2018 | SODA | A Nearly Instance Optimal Algorithm for Top- | Xi Chen, Yuanzhi Li, Jieming Mao |
| 2018 | STOC | Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing. | Zeyuan Allen-Zhu, Ankit Garg, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson |
| 2018 | STOC | An homotopy method for l | Sbastien Bubeck, Michael B. Cohen, Yin Tat Lee, Yuanzhi Li |
| 2017 | FOCS | First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2017 | FOCS | Much Faster Algorithms for Matrix Scaling. | Zeyuan Allen-Zhu, Yuanzhi Li, Rafael Mendes de Oliveira, Avi Wigderson |
| 2017 | ICML | Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2017 | ICML | Faster Principal Component Regression and Stable Matrix Chebyshev Approximation. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2017 | ICML | Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU. | Zeyuan Allen-Zhu, Yuanzhi Li |
| 2017 | ICML | Near-Optimal Design of Experiments via Regret Minimization. | Zeyuan Allen-Zhu, Yuanzhi Li, Aarti Singh, Yining Wang |
| 2017 | ICML | Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations. | Yuanzhi Li, Yingyu Liang |
| 2016 | ICML | Recovery guarantee of weighted low-rank approximation via alternating minimization. | Yuanzhi Li, Yingyu Liang, Andrej Risteski |
| 2013 | COLT | A Theoretical Analysis of NDCG Type Ranking Measures. | Yining Wang, Liwei Wang, Yuanzhi Li, Di He, Tie-Yan Liu |