| 2025 | CVPR | Rethinking Reconstruction and Denoising in the Dark: New Perspective, General Architecture and Beyond. | Tengyu Ma, Long Ma, Ziye Li, Yuetong Wang, Jinyuan Liu, Chengpei Xu, Risheng Liu |
| 2025 | ICLR | SAM 2: Segment Anything in Images and Videos. | Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rdle, Chlo Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross B. Girshick, Piotr Dollr, Christoph Feichtenhofer |
| 2025 | ICLR | Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View. | Kaiyue Wen, Zhiyuan Li, Jason S. Wang, David Leo Wright Hall, Percy Liang, Tengyu Ma |
| 2025 | ICML | Non-Asymptotic Length Generalization. | Thomas Chen, Tengyu Ma, Zhiyuan Li |
| 2025 | ICML | STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving. | Kefan Dong, Tengyu Ma |
| 2024 | AAAI | Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation. | Xiaohan Cui, Long Ma, Tengyu Ma, Jinyuan Liu, Xin Fan, Risheng Liu |
| 2024 | ICLR | Chain of Thought Empowers Transformers to Solve Inherently Serial Problems. | Zhiyuan Liu, Hong Liu, Denny Zhou, Tengyu Ma |
| 2024 | ICLR | Large Language Models as Tool Makers. | Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, Denny Zhou |
| 2024 | ICLR | Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training. | Hong Liu, Zhiyuan Li, David Leo Wright Hall, Percy Liang, Tengyu Ma |
| 2024 | ICLR | One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. | Arvind V. Mahankali, Tatsunori Hashimoto, Tengyu Ma |
| 2024 | ICML | Linguistic Calibration of Long-Form Generations. | Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto |
| 2023 | COLT | Toward L_∞Recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields. | Kefan Dong, Tengyu Ma |
| 2023 | EMNLP | Symbol tuning improves in-context learning in language models. | Jerry W. Wei, Le Hou, Andrew K. Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, Quoc V. Le |
| 2023 | ICLR | What learning algorithm is in-context learning? Investigations with linear models. | Ekin Akyrek, Dale Schuurmans, Jacob Andreas, Tengyu Ma, Denny Zhou |
| 2023 | ICLR | First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains. | Kefan Dong, Tengyu Ma |
| 2023 | ICLR | Asymptotic Instance-Optimal Algorithms for Interactive Decision Making. | Kefan Dong, Tengyu Ma |
| 2023 | ICLR | Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. | Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma |
| 2023 | ICLR | A theoretical study of inductive biases in contrastive learning. | Jeff Z. HaoChen, Tengyu Ma |
| 2023 | ICLR | How Sharpness-Aware Minimization Minimizes Sharpness? | Kaiyue Wen, Tengyu Ma, Zhiyuan Li |
| 2023 | ICML | Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models. | Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma |
| 2022 | AISTATS | Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. | Margalit R. Glasgow, Honglin Yuan, Tengyu Ma |
| 2022 | CVPR | Toward Fast, Flexible, and Robust Low-Light Image Enhancement. | Long Ma, Tengyu Ma, Risheng Liu, Xin Fan, Zhongxuan Luo |
| 2022 | ICLR | DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization. | Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron C. Courville, George Tucker, Sergey Levine |
| 2022 | ICLR | Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution. | Ananya Kumar, Aditi Raghunathan, Robbie Matthew Jones, Tengyu Ma, Percy Liang |
| 2022 | ICLR | Self-supervised Learning is More Robust to Dataset Imbalance. | Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma |
| 2022 | ICLR | An Explanation of In-context Learning as Implicit Bayesian Inference. | Sang Michael Xie, Aditi Raghunathan, Percy Liang, Tengyu Ma |
| 2022 | ICML | Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path. | Haoyuan Cai, Tengyu Ma, Simon S. Du |
| 2022 | ICML | Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification. | Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu |
| 2022 | ICML | Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation. | Kendrick Shen, Robbie M. Jones, Ananya Kumar, Sang Michael Xie, Jeff Z. HaoChen, Tengyu Ma, Percy Liang |
| 2022 | UAI | Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift. | Ananya Kumar, Tengyu Ma, Percy Liang, Aditi Raghunathan |
| 2021 | AAAI | Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. | Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang |
| 2021 | AISTATS | Active Online Learning with Hidden Shifting Domains. | Yining Chen, Haipeng Luo, Tengyu Ma, Chicheng Zhang |
| 2021 | COLT | Shape Matters: Understanding the Implicit Bias of the Noise Covariance. | Jeff Z. HaoChen, Colin Wei, Jason D. Lee, Tengyu Ma |
| 2021 | COLT | Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap. | Haike Xu, Tengyu Ma, Simon S. Du |
| 2021 | ICLR | Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization. | Kaidi Cao, Yining Chen, Junwei Lu, Nikos Archiga, Adrien Gaidon, Tengyu Ma |
| 2021 | ICLR | Optimal Regularization can Mitigate Double Descent. | Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, Tengyu Ma |
| 2021 | ICLR | Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data. | Colin Wei, Kendrick Shen, Yining Chen, Tengyu Ma |
| 2021 | ICLR | In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness. | Sang Michael Xie, Ananya Kumar, Robbie Jones, Fereshte Khani, Tengyu Ma, Percy Liang |
| 2021 | ICML | Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization. | Sang Michael Xie, Tengyu Ma, Percy Liang |
| 2021 | NAACL | Variance-reduced First-order Meta-learning for Natural Language Processing Tasks. | Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu, Jing Huang |
| 2020 | COLT | Learning Over-Parametrized Two-Layer Neural Networks beyond NTK. | Yuanzhi Li, Tengyu Ma, Hongyang R. Zhang |
| 2020 | ECCV | Robust and On-the-Fly Dataset Denoising for Image Classification. | Jiaming Song, Yann N. Dauphin, Michael Auli, Tengyu Ma |
| 2020 | ICLR | Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling. | Yuping Luo, Huazhe Xu, Tengyu Ma |
| 2020 | ICLR | Improved Sample Complexities for Deep Neural Networks and Robust Classification via an All-Layer Margin. | Colin Wei, Tengyu Ma |
| 2020 | ICML | On the Expressivity of Neural Networks for Deep Reinforcement Learning. | Kefan Dong, Yuping Luo, Tianhe Yu, Chelsea Finn, Tengyu Ma |
| 2020 | ICML | Understanding Self-Training for Gradual Domain Adaptation. | Ananya Kumar, Tengyu Ma, Percy Liang |
| 2020 | ICML | The Implicit and Explicit Regularization Effects of Dropout. | Colin Wei, Sham M. Kakade, Tengyu Ma |
| 2020 | ICML | Individual Calibration with Randomized Forecasting. | Shengjia Zhao, Tengyu Ma, Stefano Ermon |
| 2019 | COLT | On the Performance of Thompson Sampling on Logistic Bandits. | Shi Dong, Tengyu Ma, Benjamin Van Roy |
| 2019 | ICLR | Approximability of Discriminators Implies Diversity in GANs. | Yu Bai, Tengyu Ma, Andrej Risteski |
| 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 | ICLR | Fixup Initialization: Residual Learning Without Normalization. | Hongyi Zhang, Yann N. Dauphin, Tengyu Ma |
| 2018 | ACL | A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. | Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora |
| 2018 | COLT | Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. | Yuanzhi Li, Tengyu Ma, Hongyang Zhang |
| 2018 | ICLR | Learning One-hidden-layer Neural Networks with Landscape Design. | Rong Ge, Jason D. Lee, Tengyu Ma |
| 2018 | STOC | Generalization and equilibrium in generative adversarial nets (GANs) (invited talk). | Tengyu Ma |
| 2017 | COLT | On the Ability of Neural Nets to Express Distributions. | Holden Lee, Rong Ge, Tengyu Ma, Andrej Risteski, Sanjeev Arora |
| 2017 | ICCS | MiW: A domain specific modeling environment for complex molecular systems. | Tengyu Ma, Jnos Sallai |
| 2017 | ICLR | A Simple but Tough-to-Beat Baseline for Sentence Embeddings. | Sanjeev Arora, Yingyu Liang, Tengyu Ma |
| 2017 | ICLR | Identity Matters in Deep Learning. | Moritz Hardt, Tengyu Ma |
| 2017 | ICML | Generalization and Equilibrium in Generative Adversarial Nets (GANs). | Sanjeev Arora, Rong Ge, Yingyu Liang, Tengyu Ma, Yi Zhang |
| 2017 | STOC | Finding approximate local minima faster than gradient descent. | Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, Tengyu Ma |
| 2017 | STOC | Provable learning of noisy-OR networks. | Sanjeev Arora, Rong Ge, Tengyu Ma, Andrej Risteski |
| 2016 | FOCS | Polynomial-Time Tensor Decompositions with Sum-of-Squares. | Tengyu Ma, Jonathan Shi, David Steurer |
| 2016 | ICML | Provable Algorithms for Inference in Topic Models. | Sanjeev Arora, Rong Ge, Frederic Koehler, Tengyu Ma, Ankur Moitra |
| 2016 | STOC | Communication lower bounds for statistical estimation problems via a distributed data processing inequality. | Mark Braverman, Ankit Garg, Tengyu Ma, Huy L. Nguyen, David P. Woodruff |
| 2015 | COLT | Simple, Efficient, and Neural Algorithms for Sparse Coding. | Sanjeev Arora, Rong Ge, Tengyu Ma, Ankur Moitra |
| 2015 | ICML | Online Learning of Eigenvectors. | Dan Garber, Elad Hazan, Tengyu Ma |
| 2014 | ICML | Provable Bounds for Learning Some Deep Representations. | Sanjeev Arora, Aditya Bhaskara, Rong Ge, Tengyu Ma |
| 2013 | STACS | The Simulated Greedy Algorithm for Several Submodular Matroid Secretary Problems. | Tengyu Ma, Bo Tang, Yajun Wang |
| 2011 | COCOON | A New Variation of Hat Guessing Games. | Tengyu Ma, Xiaoming Sun, Huacheng Yu |