Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/6ICML 2026Poster· Deep Learning / Large Language Models

RSPO: Regularized Self-Play Alignment of Large Language Models

Xiaohang Tang · Sangwoong Yoon · Seongho Son · Huizhuo Yuan · Quanquan Gu · Ilija Bogunovic

对齐与偏好OpenReview

作者位次 #6/6ICML 2026Poster

Towards A Generative Protein Evolution Machine with DPLM-Evo

Xinyou Wang · Liang Hong · Jiasheng Ye · Zaixiang Zheng · Shujian Huang · Quanquan Gu

OpenReview

作者位次 #3/4ICML 2026Poster· Deep Learning / Large Language Models

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference

Yue Yu · Qiwei Di · Quanquan Gu · Dongruo Zhou

推理效率与系统OpenReview

作者位次 #3/3ICML 2026Poster· Reinforcement Learning / Online

Reinforcement Learning from Human Feedback with Active Queries

Kaixuan Ji · Jiafan He · Quanquan Gu

强化学习与后训练社会与人本OpenReview

作者位次 #5/5ICML 2026Oral· Applications / Chemistry, Physics, and Earth Sciences

Protein Autoregressive Modeling via Multiscale Structure Generation

Yanru Qu · Cheng-Yen Hsieh · Zaixiang Zheng · Ge Liu · Quanquan Gu

OpenReview

作者位次 #5/5ICML 2026Poster· Theory / Online Learning and Bandits

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

Kaixuan Ji · Qingyue Zhao · Heyang Zhao · Qiwei Di · Quanquan Gu

理论与学习动力学OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Attention Mechanisms

Causal Attention with Lookahead Keys

Zhuoqing Song · Peng Sun · Huizhuo Yuan · Quanquan Gu

可解释性OpenReview

作者位次 #5/5ICML 2026Poster

On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization

Dongruo Zhou · Jinghui Chen · Yuan Cao · Ziyan Yang · Quanquan Gu

OpenReview

作者位次 #4/4ICML 2026Poster· Theory / Probabilistic Methods

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

Shiyuan Zhang · Qiwei Di · Xuheng Li · Quanquan Gu

理论与学习动力学OpenReview

Quanquan Gu

获取完整研究档案

联系方式

2026 顶会论文

RSPO: Regularized Self-Play Alignment of Large Language Models

Towards A Generative Protein Evolution Machine with DPLM-Evo

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference

Reinforcement Learning from Human Feedback with Active Queries

Protein Autoregressive Modeling via Multiscale Structure Generation

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

Causal Attention with Lookahead Keys

On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

常见合作者