---
title: "Yuanzhi Li — all works — Elamur Research"
description: "All 125 works of Yuanzhi Li in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/yuanzhi-li/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yuanzhi-li/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/) / all works

# Yuanzhi Li — all works

125 works · page 1 of 2 · 1–100 · [← Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/)

**1** [2](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/works/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/works/page/2/)

1. [**LoRA: Low-Rank Adaptation of Large Language Models arXiv:2106.09685**Edward J. Hu, Yelong Shen, Phillip Wallis, et al.*2021 · 8,661 citations*](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/)
2. [**Sparks of Artificial General Intelligence: Early experiments with GPT-4 arXiv:2303.12712**Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, et al.*2023 · 2,439 citations*](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/)
3. **[A Convergence Theory for Deep Learning via Over-Parameterization ↗](https://arxiv.org/abs/1811.03962) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song*2018 · 696 citations*
4. **[Textbooks Are All You Need ↗](https://arxiv.org/abs/2306.11644) arXiv:2306.11644 · no summary yet**Suriya Gunasekar et al.*2023 · 490 citations*
5. **[A Latent Variable Model Approach to PMI-based Word Embeddings](https://md.research.elamur.ai/free/en/papers/arora-2016-latent-variable-model-approach-pmi/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Sanjeev Arora, Yuanzhi Li, Yingyu Liang, et al.*2016 · 372 citations*
6. [**Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463**Yuanzhi Li, Sébastien Bubeck, Ronen Eldan, et al.*2023 · 336 citations*](https://md.research.elamur.ai/free/en/papers/li-2023-textbooks-all-need-ii-phi/)
7. **[A Theoretical Analysis of NDCG Type Ranking Measures ↗](https://arxiv.org/abs/1304.6480) arXiv (Cornell University) · no summary yet**Yining Wang et al.*2013 · 336 citations*
8. **[Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine ↗](https://arxiv.org/abs/2311.16452) arXiv:2311.16452 · no summary yet**Harsha Nori et al.*2023 · 296 citations*
9. **[Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data ↗](https://arxiv.org/abs/1808.01204) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yingyu Liang*2018 · 295 citations*
10. **[Convergence Analysis of Two-layer Neural Networks with ReLU Activation ↗](https://arxiv.org/abs/1705.09886) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yuan Yang*2017 · 293 citations*
11. **[Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://md.research.elamur.ai/free/en/papers/arora-2018-linear-algebraic-structure-word-senses/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Sanjeev Arora, Yuanzhi Li, Yingyu Liang, et al.*2018 · 254 citations*
12. [**TinyStories: How Small Can Language Models Be and Still Speak Coherent English?**Ronen Eldan, Yuanzhi Li*English · 213 citations*](https://md.research.elamur.ai/free/en/papers/eldan-2023-tinystories-small-language-models-still/)
13. **[Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers ↗](https://arxiv.org/abs/1811.04918) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang*2018 · 193 citations*
14. **[Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning ↗](https://arxiv.org/abs/2012.09816) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2020 · 188 citations*
15. **[Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks ↗](https://arxiv.org/abs/1907.04595) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Colin Wei, Tengyu Ma*2019 · 138 citations*
16. **[Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees ↗](https://arxiv.org/abs/1807.03858) arXiv (Cornell University) · no summary yet**Yuping Luo et al.*2018 · 125 citations*
17. **[On the Convergence Rate of Training Recurrent Neural Networks ↗](https://arxiv.org/abs/1810.12065) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song*2018 · 120 citations*
18. [**Physics of Language Models: Part 3.1, Knowledge Storage and Extraction arXiv:2309.14316**Zeyuan Allen-Zhu, Yuanzhi Li*2023 · 116 citations*](https://md.research.elamur.ai/free/en/papers/allen-zhu-2023-physics-language-models-part-3/)
19. **[What Can ResNet Learn Efficiently, Going Beyond Kernels? ↗](https://arxiv.org/abs/1905.10337) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2019 · 116 citations*
20. **[Feature Purification: How Adversarial Training Performs Robust Deep Learning ↗](https://doi.org/10.1109/focs52979.2021.00098) Annual Symposium on Foundations of Computer Science · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2020 · 105 citations*
21. [**O1 Replication Journey: A Strategic Progress Report — Part 1 arXiv:2410.18982**Yiwei Qin, Xuefeng Li, Haoyang Zou, et al.*2024 · 86 citations*](https://md.research.elamur.ai/free/en/papers/qin-2024-o1-replication-journey-strategic-progress/)
22. [**Physics of Language Models: Part 3.2, Knowledge Manipulation arXiv:2309.14402**Zeyuan Allen-Zhu, Yuanzhi Li*2023 · 72 citations*](https://md.research.elamur.ai/free/en/papers/allen-zhu-2023-physics-language-models-part-3-2/)
23. **[Sparsity, variance and curvature in multi-armed bandits ↗](https://arxiv.org/abs/1711.01037) arXiv (Cornell University) · no summary yet**Sébastien Bubeck, Michael B. Cohen, Yuanzhi Li*2017 · 69 citations*
24. **[Much Faster Algorithms for Matrix Scaling ↗](https://doi.org/10.1109/focs.2017.87) Annual Symposium on Foundations of Computer Science · no summary yet**Zeyuan Allen-Zhu et al.*2017 · 68 citations*
25. **[Neon2: Finding Local Minima via First-Order Oracles ↗](https://arxiv.org/abs/1711.06673) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2017 · 63 citations*
26. **[First Efficient Convergence for Streaming k-PCA: A Global, Gap-Free, and Near-Optimal Rate ↗](https://doi.org/10.1109/focs.2017.51) Annual Symposium on Foundations of Computer Science · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2017 · 62 citations*
27. [**Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process arXiv:2407.20311**Tian Ye, Zicheng Xu, Yuanzhi Li, et al.*2024 · 58 citations*](https://md.research.elamur.ai/free/en/papers/ye-2024-physics-language-models-part-2/)
28. **[Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws ↗](https://doi.org/10.2139/ssrn.5250617) SSRN Electronic Journal · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2025 · 53 citations*
29. **[Can SGD Learn Recurrent Neural Networks with Provable Generalization? ↗](https://arxiv.org/abs/1902.01028) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2019 · 51 citations*
30. **[Towards Understanding the Mixture-Of-Experts Layer in Deep Learning ↗](https://doi.org/10.52202/068431-1675) neural information processing systems · no summary yet**Zixiang Chen et al.*2022 · 49 citations*
31. **[Near-optimal discrete optimization for experimental design: a regret minimization approach ↗](https://doi.org/10.1007/s10107-019-01464-2) Mathematical Programming · no summary yet**Zeyuan Allen-Zhu et al.*2017 · 48 citations*
32. **[An Alternative View: When Does SGD Escape Local Minima? ↗](https://arxiv.org/abs/1802.06175) arXiv (Cornell University) · no summary yet**Robert Kleinberg, Yuanzhi Li, Yuan Yang*2018 · 46 citations*
33. **[Operator scaling via geodesically convex optimization, invariant theory and polynomial identity testing ↗](https://doi.org/10.1145/3188745.3188942) ACM SIGACT Symposium on Theory of Computing (STOC) · no summary yet**Zeyuan Allen-Zhu et al.*2018 · 46 citations*
34. **[TinyGSM: achieving >80% on GSM8k with small language models ↗](https://arxiv.org/abs/2312.09241) arXiv:2312.09241 · no summary yet**Bingbin Liu et al.*2023 · 45 citations*
35. **[Physics of Language Models: Part 1, Learning Hierarchical Language Structures ↗](https://arxiv.org/abs/2305.13673) arXiv:2305.13673 · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2023 · 42 citations*
36. **[SmartPlay: A Benchmark for LLMs as Intelligent Agents ↗](https://arxiv.org/abs/2310.01557) arXiv (Cornell University) · no summary yet**Yue Wu et al.*2023 · 41 citations*
37. **[PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections ↗](https://www.usenix.org/system/files/osdi21-wang-haojie.pdf) OSDI 2021 · no summary yet**Haojie Wang et al.*2021 · 40 citations*
38. **[Chasing Nested Convex Bodies Nearly Optimally ↗](https://doi.org/10.1137/1.9781611975994.91) Society for Industrial and Applied Mathematics eBooks · no summary yet**Sébastien Bubeck et al.*2019 · 40 citations*
39. **[LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain ↗](https://arxiv.org/abs/1607.03463) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2016 · 40 citations*
40. **[Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations ↗](https://arxiv.org/abs/1712.09203) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Tengyu Ma, Hongyang Zhang*2017 · 38 citations*
41. **[Towards Understanding Mixture of Experts in Deep Learning ↗](https://arxiv.org/abs/2208.02813) arXiv (Cornell University) · no summary yet**Zixiang Chen et al.*2022 · 37 citations*
42. **[Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability ↗](https://arxiv.org/abs/2103.00065) arXiv (Cornell University) · no summary yet**Cohen, Jeremy M. et al.*2021 · 36 citations*
43. **[VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? ↗](https://arxiv.org/abs/2404.05955) arXiv (Cornell University) · no summary yet**Junpeng Liu et al.*2024 · 33 citations*
44. **[Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK ↗](https://arxiv.org/abs/2007.04596) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Tengyu Ma, Hongyang Zhang*2020 · 33 citations*
45. **[Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls ↗](https://arxiv.org/abs/1708.02105) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu et al.*2017 · 32 citations*
46. **[Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems ↗](https://arxiv.org/abs/2408.16293) arXiv:2408.16293 · no summary yet**Tian Ye et al.*2024 · 31 citations*
47. **[Positional Description Matters for Transformers Arithmetic ↗](https://arxiv.org/abs/2311.14737) arXiv:2311.14737 · no summary yet**Ruoqi Shen et al.*2023 · 30 citations*
48. **[An homotopy method for l p regression provably beyond self-concordance and in input-sparsity time ↗](https://doi.org/10.1145/3188745.3188776) ACM SIGACT Symposium on Theory of Computing (STOC) · no summary yet**Sébastien Bubeck et al.*2018 · 30 citations*
49. **[Length Generalization in Arithmetic Transformers ↗](https://arxiv.org/abs/2306.15400) arXiv:2306.15400 · no summary yet**Samy Jelassi et al.*2023 · 29 citations*
50. **[Near-optimal method for highly smooth convex optimization ↗](https://arxiv.org/abs/1812.08026) arXiv (Cornell University) · no summary yet**Sébastien Bubeck et al.*2018 · 28 citations*
51. **[Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions ↗](https://arxiv.org/abs/2209.11215) arXiv (Cornell University) · no summary yet**Sitan Chen et al.*2022 · 25 citations*
52. **[Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates ↗](https://arxiv.org/abs/1611.03819) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yingyu Liang, Andrej Risteski*2016 · 25 citations*
53. **[Backward Feature Correction: How Deep Learning Performs Deep Learning ↗](https://arxiv.org/abs/2001.04413) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2020 · 24 citations*
54. **[Vision Transformers Provably Learn Spatial Structure ↗](https://doi.org/10.52202/068431-2741) neural information processing systems · no summary yet**Samy Jelassi, Michael Sander, Yuanzhi Li*2022 · 23 citations*
55. **[Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU ↗](https://arxiv.org/abs/1701.01722) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2017 · 23 citations*
56. **[Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning ↗](https://arxiv.org/abs/2105.15134) arXiv (Cornell University) · no summary yet**Zixin Wen, Yuanzhi Li*2021 · 22 citations*
57. **[Complexity of Highly Parallel Non-Smooth Convex Optimization ↗](https://arxiv.org/abs/1906.10655) arXiv (Cornell University) · no summary yet**Sébastien Bubeck et al.*2019 · 22 citations*
58. **[A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model ↗](https://doi.org/10.1137/1.9781611975031.160) Society for Industrial and Applied Mathematics eBooks · no summary yet**Xi Chen, Yuanzhi Li, Jieming Mao*2018 · 22 citations*
59. **[Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations ↗](https://arxiv.org/abs/1706.04097) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yingyu Liang*2017 · 22 citations*
60. **[An optimal algorithm for bandit convex optimization ↗](https://arxiv.org/abs/1603.04350) arXiv (Cornell University) · no summary yet**Elad Hazan, Yuanzhi Li*2016 · 21 citations*
61. **[RAND-WALK: A Latent Variable Model Approach to Word Embeddings ↗](https://arxiv.org/abs/1502.03520) arXiv (Cornell University) · no summary yet**Sanjeev Arora et al.*2015 · 21 citations*
62. **[Efficient RLHF: Reducing the Memory Usage of PPO ↗](https://arxiv.org/abs/2309.00754) arXiv:2309.00754 · no summary yet**Michael Santacroce et al.*2023 · 20 citations*
63. **[What Matters In The Structured Pruning of Generative Language Models? ↗](https://arxiv.org/abs/2302.03773) arXiv (Cornell University) · no summary yet**Michael Santacroce et al.*2023 · 20 citations*
64. **[Plan, Eliminate, and Track — Language Models are Good Teachers for Embodied Agents ↗](https://arxiv.org/abs/2305.02412) arXiv (Cornell University) · no summary yet**Yue Wu et al.*2023 · 20 citations*
65. **[Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals ↗](https://doi.org/10.52202/075280-0048) neural information processing systems · no summary yet**Yue Wu et al.*2023 · 20 citations*
66. **[Near Optimal Methods for Minimizing Convex Functions with Lipschitz p-th Derivatives ↗](https://openalex.org/W2965963244) Conference on Learning Theory · no summary yet**Alexander Vladimirovich Gasnikov et al.*2019 · 20 citations*
67. **[Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition ↗](https://arxiv.org/abs/1607.06017) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2016 · 20 citations*
68. **[The probability flow ODE is provably fast ↗](https://doi.org/10.52202/075280-2998) neural information processing systems · no summary yet**Sitan Chen et al.*2023 · 19 citations*
69. **[SPRING: Studying the Paper and Reasoning to Play Games ↗](https://arxiv.org/abs/2305.15486) arXiv (Cornell University) · no summary yet**Yue Wu et al.*2023 · 19 citations*
70. **[Recovery guarantee of weighted low-rank approximation via alternating minimization ↗](https://arxiv.org/abs/1602.02262) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yingyu Liang, Andrej Risteski*2016 · 17 citations*
71. **[LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks ↗](https://aclanthology.org/2025.coling-industry.55/) Proceedings of the 31st International Conference on Computational Linguistics: Industry Track · no summary yet**Akshara Prabhakar et al.*2025 · 14 citations*
72. **[How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding ↗](https://arxiv.org/abs/2303.04245) arXiv (Cornell University) · no summary yet**Yuchen Li, Yuanzhi Li, Andrej Risteski*2023 · 14 citations*
73. **[Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization ↗](https://arxiv.org/abs/2108.11371) arXiv (Cornell University) · no summary yet**Difan Zou et al.*2021 · 13 citations*
74. **[Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits ↗](https://arxiv.org/abs/1802.03386) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Sébastien Bubeck, Yuanzhi Li*2018 · 13 citations*
75. **[Toward Understanding Why Adam Converges Faster Than SGD for Transformers ↗](https://arxiv.org/abs/2306.00204) arXiv (Cornell University) · no summary yet**Yan Pan, Yuanzhi Li*2023 · 12 citations*
76. **[Online Improper Learning with an Approximation Oracle ↗](https://arxiv.org/abs/1804.07837) arXiv (Cornell University) · no summary yet**Elad Hazan et al.*2018 · 12 citations*
77. **[Towards understanding how momentum improves generalization in deep learning ↗](https://arxiv.org/abs/2207.05931) arXiv (Cornell University) · no summary yet**Samy Jelassi, Yuanzhi Li*2022 · 11 citations*
78. **[Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions ↗](https://arxiv.org/abs/2106.02619) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2021 · 11 citations*
79. **[When can Wasserstein GANs minimize Wasserstein Distance ↗](https://arxiv.org/abs/2003.04033) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Zehao Dou*2020 · 11 citations*
80. **[Learning Mixtures of Linear Regressions with Nearly Optimal Complexity ↗](https://arxiv.org/abs/1802.07895) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yingyu Liang*2018 · 10 citations*
81. **[A law of robustness for two-layers neural networks ↗](https://arxiv.org/abs/2009.14444) arXiv (Cornell University) · no summary yet**Sébastien Bubeck, Yuanzhi Li, Anant Raj*2020 · 9 citations*
82. **[Algorithms and matching lower bounds for approximately-convex optimization ↗](https://openalex.org/W2556098900) neural information processing systems · no summary yet**Yuanzhi Li, Andrej Risteski*2016 · 9 citations*
83. **[When Is Generalizable Reinforcement Learning Tractable? ↗](https://arxiv.org/abs/2101.00300) arXiv (Cornell University) · no summary yet**Dhruv Malik, Yuanzhi Li, Pradeep Ravikumar*2021 · 8 citations*
84. **[Faster Principal Component Regression and Stable Matrix Chebyshev Approximation ↗](https://arxiv.org/abs/1608.04773) arXiv (Cornell University) · no summary yet**Zeyuan Allen-Zhu, Yuanzhi Li*2016 · 8 citations*
85. **[SPRING: Studying Papers and Reasoning to play Games ↗](https://doi.org/10.52202/075280-0983) neural information processing systems · no summary yet**Yue Wu et al.*2023 · 6 citations*
86. **[The Mechanism of Prediction Head in Non-Contrastive Self-Supervised Learning ↗](https://doi.org/10.52202/068431-1798) neural information processing systems · no summary yet**Zixin Wen, Yuanzhi Li*2022 · 6 citations*
87. **[Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels ↗](https://openalex.org/W3212082792) neural information processing systems · no summary yet**Stefani Karp et al.*2021 · 6 citations*
88. **[Improved Path-length Regret Bounds for Bandits ↗](https://arxiv.org/abs/1901.10604) arXiv (Cornell University) · no summary yet**Sébastien Bubeck et al.*2019 · 6 citations*
89. **[Provably Learning a Multi-head Attention Layer ↗](https://doi.org/10.1145/3717823.3718174) ACM Symposium on Theory of Computing (STOC) · no summary yet**Sitan Chen, Yuanzhi Li*2025 · 5 citations*
90. **[AgentKit: Structured LLM Reasoning with Dynamic Graphs ↗](https://arxiv.org/abs/2404.11483) arXiv (Cornell University) · no summary yet**Yue Wu et al.*2024 · 5 citations*
91. **[How Does Adaptive Optimization Impact Local Neural Network Geometry? ↗](https://doi.org/10.52202/075280-0366) neural information processing systems · no summary yet**Kaiqi Jiang, Dhruv Malik, Yuanzhi Li*2023 · 5 citations*
92. **[Learning (Very) Simple Generative Models Is Hard ↗](https://arxiv.org/abs/2205.16003) arXiv (Cornell University) · no summary yet**Sitan Chen, Jerry Li, Yuanzhi Li*2022 · 5 citations*
93. **[Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs ↗](https://arxiv.org/abs/2201.07206) arXiv (Cornell University) · no summary yet**Sitan Chen et al.*2022 · 5 citations*
94. **[Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without ↗](https://arxiv.org/abs/1904.12233) arXiv (Cornell University) · no summary yet**Sébastien Bubeck et al.*2019 · 5 citations*
95. **[Mixture of Parrots: Experts improve memorization more than reasoning ↗](https://arxiv.org/abs/2410.19034) arXiv (Cornell University) · no summary yet**Samy Jelassi et al.*2024 · 4 citations*
96. **[LLM360 K2: Building a 65B 360-Open-Source Large Language Model from Scratch ↗](https://arxiv.org/abs/2501.07124) arXiv (Cornell University) · no summary yet**Zhengzhong Liu et al.*2025 · 3 citations*
97. **[Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning ↗](https://doi.org/10.1609/aaai.v38i13.29354) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Ruiqian Nai et al.*2024 · 3 citations*
98. **[The Benefits of Mixup for Feature Learning ↗](https://arxiv.org/abs/2303.08433) arXiv (Cornell University) · no summary yet**Difan Zou et al.*2023 · 3 citations*
99. **[Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning ↗](https://doi.org/10.1109/focs52979.2021.00097) Annual Symposium on Foundations of Computer Science · no summary yet**Yuanzhi Li, Ruosong Wang, Lin Forrest Yang*2021 · 3 citations*
100. **[Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity ↗](https://arxiv.org/abs/2106.07814) arXiv (Cornell University) · no summary yet**Dhruv Malik et al.*2021 · 3 citations*

**1** [2](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/works/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/works/page/2/)