PPaperPicks

Yuanzhi Li

13 papers at tracked venues · 13 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

ICLR ×9ICML ×2AAAI ×1NeurIPS ×1

Frequent coauthors

Zeyuan Allen-Zhu
DBLP profile ↗ORCID search ↗
×3
Binghui Li
DBLP profile ↗ORCID search ↗
×2
Tian Ye
DBLP profile ↗ORCID search ↗
×2
Samy Jelassi
DBLP profile ↗ORCID search ↗
×1
Kaiqi Jiang
DBLP profile ↗ORCID search ↗
×1
Ruiqian Nai
DBLP profile ↗ORCID search ↗
×1
Aakash Lahoti
DBLP profile ↗ORCID search ↗
×1
Yue Wu
DBLP profile ↗ORCID search ↗
×1
Zixiang Chen
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
    ICLR 2025 ·
    Binghui Li
    DBLP profile ↗ORCID search ↗
  2. Mixture of Parrots: Experts improve memorization more than reasoning
    ICLR 2025 ·
    Samy Jelassi
    DBLP profile ↗ORCID search ↗
  3. On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
    ICML 2025 ·
    Binghui Li
    DBLP profile ↗ORCID search ↗
  4. Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
    ICLR 2025 ·
    Tian Ye
    DBLP profile ↗ORCID search ↗
  5. Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
    ICLR 2025 ·
    Tian Ye
    DBLP profile ↗ORCID search ↗
  6. Physics of Language Models: Part 3.2, Knowledge Manipulation
    ICLR 2025 ·
    Zeyuan Allen-Zhu
    DBLP profile ↗ORCID search ↗
  7. Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
    ICLR 2025 ·
    Zeyuan Allen-Zhu
    DBLP profile ↗ORCID search ↗
  8. Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
    NeurIPS 2025 ·
    Kaiqi Jiang
    DBLP profile ↗ORCID search ↗
  9. Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
    ICML 2024 ·
    Zeyuan Allen-Zhu
    DBLP profile ↗ORCID search ↗
  10. Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning
    AAAI 2024 ·
    Ruiqian Nai
    DBLP profile ↗ORCID search ↗
  11. Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
    ICLR 2024 ·
    Aakash Lahoti
    DBLP profile ↗ORCID search ↗
  12. SmartPlay : A Benchmark for LLMs as Intelligent Agents
    ICLR 2024 ·
    Yue Wu
    DBLP profile ↗ORCID search ↗
  13. Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
    ICLR 2024 ·
    Zixiang Chen
    DBLP profile ↗ORCID search ↗