paper-with-me

홈 › Papers

GUICourse: From General Vision Language Models to Versatile GUI Agents

2024-06-17 · Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan YAO, Yankai Lin, Zhiyuan Liu, Maosong Sun

Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile agents to help humans finish GUI navigation tasks. However, current VLMs are challenged in terms of fundamental abilities (OCR and grounding) and GUI knowledge (the functions and control methods of GUI elements), preventing them from becoming practical GUI agents. To solve these challenges, we contribute GUICourse, a suite of datasets to train visual-based GUI agents from general VLMs. First, we introduce the GUIEnv dataset to strengthen the OCR and grounding capabilities of VLMs. Then, we introduce the GUIAct and GUIChat datasets to enrich their knowledge of GUI components and interactions. Experiments demonstrate that our GUI agents have better performance on common GUI tasks than their baseline VLMs. Even the small-size GUI agent (with 3.1B parameters) can still work well on single-step and multi-step GUI tasks. Finally, we analyze the different varieties in the training stage of this agent by ablation study. Our source codes and datasets are released at https://github.com/yiye3/GUICourse.

📄 PDF Abstract BibTeX arXiv:2406.11317

Code (1)

yiye3/guicourse 공식 구현

Tasks

Natural Language Visual GroundingOptical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation

2025-12-22 · Sihao Lin, Zerui Li, Xunyi Zhao, Gengze Zhou 외 arxiv

Despite remarkable progress in Vision-Language Navigation (VLN), existing benchmarks remain confined to fixed, small-scale datasets with naive physical simulation. These shortcomings limit the insight that the benchmarks…

Vision-Language Navigation

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

2025-10-10 · Lianhao Zhou, Hongyi Ling, Cong Fu, Yepeng Huang 외 arxiv

Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accele…

LLM-mediated Dynamic Plan Generation with a Multi-Agent Approach

2025-04-02 · Reo Abe, Akifumi Ito, Kanata Takayasu, Satoshi Kurihara

Planning methods with high adaptability to dynamic environments are crucial for the development of autonomous and versatile robots. We propose a method for leveraging a large language model (GPT-4o) to automatically gene…

Autonomous VehiclesLanguage ModelingLanguage ModellingLarge Language Model

OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

2026-03-12 · Yibin Yan, Jilan Xu, Shangzhe Di, Haoning Wu 외 arxiv

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing n…

Representation LearningSpatial Reasoning

VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding

2024-06-18 · Xiang Li, Jian Ding, Mohamed Elhoseiny

We introduce a new benchmark designed to advance the development of general-purpose, large-scale vision-language models for remote sensing images. Although several vision-language datasets in remote sensing have been pro…

Image CaptioningQuestion AnsweringVisual GroundingVisual Question Answering