Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/7ICML 2026Poster· Reinforcement Learning / Deep RL

Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning

Cheng Xin · Shuo He · Lang Feng · Haiyang Xu · Ming Yan · Lei Feng · Bo An

强化学习与后训练智能体与工具OpenReview

作者位次 #5/5ICML 2026Poster· Reinforcement Learning / Deep RL

Task-Aware Exploration via a Predictive Bisimulation Metric

Dayang Liang · Ruihan LIU · Lipeng Wan · Yunlong Liu · Bo An

强化学习与后训练社会与人本OpenReview

作者位次 #4/5ICML 2026Poster· General Machine Learning / Supervised Learning

When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer

Shuqi Liu · Yuzhou Cao · Lei Feng · Bo An · Luke Ong

OpenReview

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

AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search

Qingyao Li · Weiwen Liu · Weinan Zhang · Yong Yu · Bo An

安全检索与知识代码OpenReview

作者位次 #9/9ICML 2026Poster· Deep Learning / Large Language Models

REAR: Test-time Preference Realignment through Reward Decomposition

Fuxiang Zhang · Pengcheng Wang · Chenran Li · Yi-Chen Li · Yuxin Chen · Lang Feng · Chenfeng Xu · Masayoshi Tomizuka · Bo An

对齐与偏好OpenReview

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

Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping

Jianxiong Zhang · Bing Guo · Yuming Jiang · Haobo Wang · Bo An · Sean Du

推理安全可解释性OpenReview

作者位次 #6/8ICML 2026Poster· Reinforcement Learning / Everything Else

Adversarial Dual On-Policy Distillation from Expressive Teacher

Zhenglin Wan · Jingxuan Wu · Xingrui Yu · Chubin Zhang · Mingcong Lei · Bo An · Ivor Tsang · Yang You

强化学习与后训练安全理论与学习动力学OpenReview

作者位次 #12/15ICML 2026Poster· Reinforcement Learning / Multi-agent

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

Simin Li · Zihao Mao · Zheng Yuwei · Linhao Wang · Ruixiao Xu · Chengdong Ma · Zhiqian Liu · Xin Yu · Yuqing Ma · Xin Wang · Jie Luo · Bo An · Yaodong Yang · Weifeng Lv · Xianglong Liu

智能体与工具强化学习与后训练OpenReview

作者位次 #5/7ICML 2026Poster· Applications / Computer Vision

Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching

Jingxuan Wu · Zhenglin Wan · Xingrui Yu · Yuzhe YANG · Bo An · Ivor Tsang · Yang You

多模态OpenReview

作者位次 #8/9ICML 2026Poster· Reinforcement Learning / Deep RL

Covariance Volume Maximization for Embodied Latent Exploration in Deep Reinforcement Learning

Yiming Wang · Yiheng Zhang · Kaiyan Zhao · Xingjie Zuo · Xingyu Liu · Xuetao Li · Furui Liu · Bo An · Leong Hou U

强化学习与后训练OpenReview

作者位次 #10/10ICML 2026Poster· Reinforcement Learning / Online

Generative Online Reinforcement Learning

Chubin Zhang · Zhenglin Wan · Feng Chen · Fuchao Yang · Lang Feng · Yaxin Zhou · Xingrui Yu · Yang You · Ivor Tsang · Bo An

强化学习与后训练OpenReview

作者位次 #5/5ICML 2026Poster· Social Aspects / Fairness

Self-correcting for Debiasing Large Language Models

Xuan Feng · Shuai Zhao · Luwei Xiao · Tianlong Gu · Bo An

社会与人本OpenReview

Bo An

获取完整研究档案

联系方式