Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/8ICML 2026Poster· Deep Learning / Large Language Models

Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification

Tianyi Wang · Long Li · Hongcan Guo · Yibiao Chen · Yixia Li · Yong Wang · Yun Chen · Guanhua CHEN

强化学习与后训练OpenReview

作者位次 #3/8ACL 2026Poster· Natural Language Processing

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

Wenkai Wang · Xiyun Li · Hongcan Guo · Wenhao Yu · Tianqing Fang · Haitao Mi · Dong Yu · Shengyu Zhang

摘要

Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogeneous elements and dense layouts, models typically grasp semantic intent yet fail to achieve precise localization. While scaling sampling attempts (...

评测与基准智能体与工具可解释性OpenReview 项目页

作者位次 #2/4AAAI 2026Poster· Artificial Intelligence

A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models

Wenkai Wang · Hongcan Guo · Zheqi Lv · Shengyu Zhang

多模态强化学习与后训练评测与基准OpenReview

Hongcan Guo

获取完整研究档案

联系方式

2026 顶会论文

Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models

常见合作者