Scholar
Quanquan Gu
Google Scholar ID: GU9HgNAAAAAJ
Associate Professor of Computer Science, UCLA
Citations & Impact
Citations
21,045
H-index
69
i10-index
221
Publications
20
Co-authors
77
list available
Publications
Cited
3
Resume (English only)
Academic Achievements
- Published numerous papers in top-tier conferences including NeurIPS, ICML, ICLR, and COLT, such as:
- “Tensor Product Attention Is All You Need” (NeurIPS 2025, Spotlight)
- “MARS: Unleashing the Power of Variance Reduction for Training Large Models” (ICML 2025)
- “Self-Play Preference Optimization for Language Model Alignment” (ICLR 2025)
- “Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation” (NeurIPS 2024)
- “Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models” (ICML 2024)
- “Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data” (NeurIPS 2023)
- “Why Does Sharpness-Aware Minimization Generalize Better Than SGD?” (NeurIPS 2023)
- “Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes” (ICML 2023)
- “Benign Overfitting for Two-layer ReLU Convolutional Neural Networks” (ICML 2023)
- “Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning” (COLT 2023)
- “Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs” (NeurIPS 2022, Oral)
- “Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions” (NeurIPS 2022)
- Organized the NeurIPS 2023 workshop “New Frontiers of AI for Drug Discovery and Development”
