paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
YH

Yuwei Hu

ACL 2026×2评测与基准智能体与工具多模态强化学习与后训练
新星分贡献者
49
一作贡献0
核心/参与17
方向广度8
合作网络12
0 一作 · 2 篇 · ACL 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

2
作者位次 #2/10ACL 2026Poster· Natural Language Processing

M irror CAPTCHA : Wild CAPTCHA , Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents

Xiangyu Wu · Yuwei Hu · Tianyu Cui · Yueying Tian · Qing-Guo Chen · Zhao Xu · Weihua Luo · Kaifu Zhang · Yang Yang · Jianfeng Lu

摘要

The path to fully autonomous web agents is currently hindered by a critical bottleneck: their limited ability to handle CAPTCHA. Existing agent benchmarks largely ignore this practical challenge, failing to evaluate an agent’s real-world capacity to solve CAPTCHA. To bridge this gap, we conduct a...

评测与基准智能体与工具多模态OpenReview 项目页
作者位次 #4/12ACL 2026Findings· Findings of ACL

LPO : Towards Accurate GUI Agent Interaction via Location Preference Optimization

Jiaqi Tang · Yu Xia · Yi-Feng Wu · Yuwei Hu · Chen Yuhui · Qing-Guo Chen · Xiaogang Xu · Xiangyu Wu · Hao LU · Yanqing Ma · Shiyin Lu · Qifeng Chen

摘要

The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of supervised fine-tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods fac...

强化学习与后训练智能体与工具评测与基准OpenReview 项目页

常见合作者