---
title: "Yuanzhi Li — all works, page 2 — 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/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yuanzhi-li/works/page/2/)

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

# Yuanzhi Li — all works

125 works · page 2 of 2 · 101–125 · [← Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/)

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

101. **[The Well Tempered Lasso ↗](https://arxiv.org/abs/1806.03190) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Yoram Singer*2018 · 3 citations*
102. **[Competitively Chasing Convex Bodies ↗](https://doi.org/10.1137/20m1312332) SIAM Journal on Computing · no summary yet**Sébastien Bubeck et al.*2023 · 2 citations*
103. **[Learning Polynomial Transformations ↗](https://arxiv.org/abs/2204.04209) arXiv (Cornell University) · no summary yet**Sitan Chen et al.*2022 · 2 citations*
104. **[On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization ↗](https://arxiv.org/abs/2109.14213) arXiv (Cornell University) · no summary yet**Zehao Dou, Yuanzhi Li*2021 · 2 citations*
105. **[Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models ↗](https://arxiv.org/abs/2603.12248) arXiv (Cornell University) · no summary yet**Samy Jelassi et al.*2026 · 1 citation*
106. **[Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs ↗](https://arxiv.org/abs/2403.15707) arXiv (Cornell University) · no summary yet**Aakash Lahoti et al.*2024 · 1 citation*
107. **[Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY ↗](https://doi.org/10.1007/s10957-024-02491-6) Journal of Optimization Theory and Applications · no summary yet**Eric Luxenberg et al.*2024 · 1 citation*
108. **[On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics ↗](https://arxiv.org/abs/2306.01271) arXiv (Cornell University) · no summary yet**Li, Binghui, Yuanzhi Li*2023 · 1 citation*
109. **[On the Importance of Contrastive Loss in Multimodal Learning ↗](https://arxiv.org/abs/2304.03717) arXiv (Cornell University) · no summary yet**Yunwei Ren, Yuanzhi Li*2023 · 1 citation*
110. **[Complete Policy Regret Bounds for Tallying Bandits ↗](https://arxiv.org/abs/2204.11174) arXiv (Cornell University) · no summary yet**Dhruv Malik, Yuanzhi Li, Aarti Singh*2022 · 1 citation*
111. **[Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods ↗](https://arxiv.org/abs/1607.03360) arXiv (Cornell University) · no summary yet**Yuanzhi Li, Andrej Risteski*2016 · 1 citation*
112. **[Systematic Data Structure Lower Bounds via the Query-With-Sketch Model ↗](https://doi.org/10.4230/lipics.ccc.2026.41) arXiv (Cornell University) · no summary yet**Sumegha Garg et al.*2026*
113. **[SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding ↗](https://arxiv.org/abs/2603.09036) arXiv (Cornell University) · no summary yet**Renos Zabounidis et al.*2026*
114. **[Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark ↗](https://arxiv.org/abs/2503.20786) arXiv (Cornell University) · no summary yet**Sondos Mahmoud Bsharat et al.*2025*
115. **[Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability ↗](https://doi.org/10.52202/085713-1075) neural information processing systems · no summary yet**Kaiqi Jiang, Jeremy Cohen, Yuanzhi Li*2025*
116. **[M³VIR: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation ↗](https://arxiv.org/abs/2509.16873) arXiv (Cornell University) · no summary yet**Yuanzhi Li et al.*2025*
117. **[Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data ↗](https://arxiv.org/abs/2410.08503) arXiv (Cornell University) · no summary yet**Li, Binghui, Yuanzhi Li*2024*
118. **[Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts ↗](https://arxiv.org/abs/2409.00879) arXiv (Cornell University) · no summary yet**Youngseog Chung et al.*2024*
119. **[How Does Overparameterization Affect Features? ↗](https://arxiv.org/abs/2407.00968) arXiv (Cornell University) · no summary yet**Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li*2024*
120. **[The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks ↗](https://arxiv.org/abs/2306.11680) arXiv (Cornell University) · no summary yet**Yuan Cao et al.*2023*
121. **[Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP ↗](https://arxiv.org/abs/2310.00927) arXiv (Cornell University) · no summary yet**Zixiang Chen et al.*2023*
122. **[Simple Mechanisms for Representing, Indexing and Manipulating Concepts ↗](https://arxiv.org/abs/2310.12143) arXiv (Cornell University) · no summary yet**Yuanzhi Li et al.*2023*
123. **[Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality ↗](https://arxiv.org/abs/2305.02955) arXiv (Cornell University) · no summary yet**Dhruv Malik et al.*2023*
124. **[Dissecting adaptive methods in GANs ↗](https://arxiv.org/abs/2210.04319) arXiv (Cornell University) · no summary yet**Samy Jelassi et al.*2022*
125. **[An homotopy method for p regression provably beyond self-concordance and in input-sparsity time ↗](https://arxiv.org/abs/1711.01328) arXiv (Cornell University) · no summary yet**Sébastien Bubeck et al.*2017*

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