中文
相关论文

相关论文: Learn where to Click from Yourself: On-Policy Self…

200 篇论文

Developing lightweight, on-device vision-language GUI agents is essential for efficient cross-platform automated interaction. However, current on-device agents are constrained by limited model capacity, and further performance improvements…

人工智能 · 计算机科学 2026-05-11 Yubin Wu , Zicheng Cai , Liping Ning , Hua Wang , Zhi Chen , Yaohua Tang , Hao Chen

Graphical User Interface (GUI) grounding, the task of mapping natural language instructions to precise screen coordinates, is fundamental to autonomous GUI agents. While existing methods achieve strong performance through extensive…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Yong Du , Yuchen Yan , Fei Tang , Zhengxi Lu , Chang Zong , Weiming Lu , Shengpei Jiang , Yongliang Shen

Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging, especially…

人工智能 · 计算机科学 2025-05-27 Xinbin Yuan , Jian Zhang , Kaixin Li , Zhuoxuan Cai , Lujian Yao , Jie Chen , Enguang Wang , Qibin Hou , Jinwei Chen , Peng-Tao Jiang , Bo Li

Graphical User Interface (GUI) tasks are vital for automating workflows such as software testing, user interface navigation. For users, the GUI is the most intuitive platform for interacting with a computer. Previous work identified a key…

计算与语言 · 计算机科学 2025-03-10 Zheng Hui , Yinheng Li , Dan zhao , Tianyi Chen , Colby Banbury , Kazuhito Koishida

Autonomous graphical user interface (GUI) agents rely on accurate GUI grounding, which maps language instructions to on-screen coordinates, to execute user commands. However, current models, whether trained via supervised fine-tuning (SFT)…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Shaojie Zhang , Pei Fu , Ruoceng Zhang , Jiahui Yang , Anan Du , Xiuwen Xi , Shaokang Wang , Ying Huang , Bin Qin , Zhenbo Luo , Jian Luan

Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate on-screen coordinates for actions such as clicks and keystrokes. However, recent Vision Language…

The rapid advancement of vision-language models has catalyzed the emergence of GUI agents, which hold immense potential for automating complex tasks, from online shopping to flight booking, thereby alleviating the burden of repetitive…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Zhongyin Zhao , Yuan Liu , Yikun Liu , Haicheng Wang , Le Tian , Xiao Zhou , Yangxiu You , Zilin Yu , Yang Yu , Jie Zhou

Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot…

人工智能 · 计算机科学 2025-11-18 SeokJoo Kwak , Jihoon Kim , Boyoun Kim , Jung Jae Yoon , Wooseok Jang , Jeonghoon Hong , Jaeho Yang , Yeong-Dae Kwon

Graphical User Interface (GUI) grounding maps natural language instructions to precise interface locations for autonomous interaction. Current reinforcement learning approaches use binary rewards that treat elements as hit-or-miss targets,…

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

机器学习 · 计算机科学 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks.…

人工智能 · 计算机科学 2026-05-25 Aristotelis Lazaridis , Dylan Bates , Aman Sharma , Brian King , Vincent Lu , Jack FitzGerald

Recent advances in vision-language models (VLMs) and reinforcement learning (RL) have driven progress in GUI automation. However, most existing methods rely on static, one-shot visual inputs and passive perception, lacking the ability to…

人工智能 · 计算机科学 2026-01-16 Chen Chen , Jiawei Shao , Dakuan Lu , Haoyi Hu , Xiangcheng Liu , Hantao Yao , Wu Liu

Graphical User Interface (GUI) agents are designed to automate complex tasks on digital devices, such as smartphones and desktops. Most existing GUI agents interact with the environment through extracted structured data, which can be…

人机交互 · 计算机科学 2024-02-26 Kanzhi Cheng , Qiushi Sun , Yougang Chu , Fangzhi Xu , Yantao Li , Jianbing Zhang , Zhiyong Wu

Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding models achieve promising performance to simulate the mouse…

人机交互 · 计算机科学 2026-01-13 Zeyi Liao , Yadong Lu , Boyu Gou , Huan Sun , Ahmed Awadallah

Graphical User Interface (GUI) action grounding is a critical step in GUI automation that maps language instructions to actionable elements on GUI screens. Most recent works of GUI action grounding leverage large GUI datasets to fine-tune…

计算与语言 · 计算机科学 2025-01-28 Yue Fan , Handong Zhao , Ruiyi Zhang , Yu Shen , Xin Eric Wang , Gang Wu

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

On-Policy Self-Distillation (OPSD) is a unified learning framework in which a single large language model acts simultaneously as both teacher and student. Unlike conventional knowledge distillation that relies on a separate, often larger…

人机交互 · 计算机科学 2026-05-22 Fangming Cui , Sunan Li , Jiahong Li

GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural language instructions. However, grounding on GUI screenshots…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Siqi Pei , Liang Tang , Tiaonan Duan , Long Chen , Shuxian Li , Kaer Huang , Yanzhe Jing , Yiqiang Yan , Bo Zhang , Chenghao Jiang , Borui Zhang , Jiwen Lu

Graphical user interface (GUI) agents have recently emerged as an intriguing paradigm for human-computer interaction, capable of automatically executing user instructions to operate intelligent terminal devices. However, when encountering…

机器学习 · 计算机科学 2025-11-25 Zheng Wu , Pengzhou Cheng , Zongru Wu , Lingzhong Dong , Zhuosheng Zhang

GUI grounding, the task of mapping natural-language instructions to pixel coordinates, is crucial for autonomous agents, yet remains difficult for current VLMs. The core bottleneck is reliable patch-to-pixel mapping, which breaks when…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Suyuchen Wang , Tianyu Zhang , Ahmed Masry , Christopher Pal , Spandana Gella , Bang Liu , Perouz Taslakian
‹ 上一页 1 2 3 10 下一页 ›