中文
相关论文

相关论文: GUI-GENESIS: Automated Synthesis of Efficient Envi…

200 篇论文

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vision tasks. The main contribution is a procedural world…

计算机视觉与模式识别 · 计算机科学 2017-10-19 Apostolia Tsirikoglou , Joel Kronander , Magnus Wrenninge , Jonas Unger

With the advent of AI agents, automatic scientific discovery has become a tenable goal. Many recent works scaffold agentic systems that can perform machine learning research, but don't offer a principled way to train such agents -- and…

人工智能 · 计算机科学 2026-03-19 Ziyang Cai , Harkirat Behl

With the widespread adoption of Graphical User Interface (GUI) agents for automating GUI interaction tasks, substantial research focused on improving GUI perception to ground task instructions into concrete action steps. However, the step…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Xuan Wang , Siyuan Su , Quantong Fu , Yongxiang Hu , Yangfan Zhou

Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on natural language instructions. The increasing accuracy of…

密码学与安全 · 计算机科学 2026-04-15 Guohong Liu , Jialei Ye , Jiacheng Liu , Yuanchun Li , Wei Liu , Pengzhi Gao , Jian Luan , Yunxin Liu

Graphical User Interface (GUI) is ubiquitous in almost all modern desktop software, mobile applications, and online websites. A good GUI design is crucial to the success of the software in the market, but designing a good GUI which requires…

人机交互 · 计算机科学 2021-02-02 Tianming Zhao , Chunyang Chen , Yuanning Liu , Xiaodong Zhu

Reinforcement Learning (RL) has the potential to improve the robustness of GUI agents in stochastic environments, yet training is highly sensitive to the quality of the reward function. Existing reward approaches struggle to achieve both…

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

Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has been limited by two structural bottlenecks: existing open-source agentic training data are narrow in…

计算与语言 · 计算机科学 2026-03-13 Yuanjie Lyu , Chengyu Wang , Lei Shen , Jun Huang , Tong Xu

Customizing pre-trained text-to-image generation model has attracted massive research interest recently, due to its huge potential in real-world applications. Although existing methods are able to generate creative content for a novel…

计算机视觉与模式识别 · 计算机科学 2024-05-10 Yufan Zhou , Ruiyi Zhang , Jiuxiang Gu , Tong Sun

Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities to enhance productivity on digital devices. Compared to…

人机交互 · 计算机科学 2025-07-31 Xinyi Liu , Xiaoyi Zhang , Ziyun Zhang , Yan Lu

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

计算机视觉与模式识别 · 计算机科学 2020-08-20 Harkirat Singh Behl , Atılım Güneş Baydin , Ran Gal , Philip H. S. Torr , Vibhav Vineet

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

计算机视觉与模式识别 · 计算机科学 2019-04-29 Amlan Kar , Aayush Prakash , Ming-Yu Liu , Eric Cameracci , Justin Yuan , Matt Rusiniak , David Acuna , Antonio Torralba , Sanja Fidler

Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i) synthesizing new features from standards or research papers into production code; (ii)…

The development of high-quality datasets is crucial for benchmarking and advancing research in Graphical User Interface (GUI) agents. Despite their importance, existing datasets are often constructed under idealized conditions, overlooking…

人工智能 · 计算机科学 2025-06-18 Jingqi Yang , Zhilong Song , Jiawei Chen , Mingli Song , Sheng Zhou , linjun sun , Xiaogang Ouyang , Chun Chen , Can Wang

We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…

计算机视觉与模式识别 · 计算机科学 2020-06-04 Igor Kviatkovsky , Nadav Bhonker , Gerard Medioni

Modern world models require costly and time-consuming collection of large video datasets with action demonstrations by people or by environment-specific agents. To simplify training, we focus on using many virtual environments for…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Nedko Savov , Naser Kazemi , Mohammad Mahdi , Danda Pani Paudel , Xi Wang , Luc Van Gool

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Xuemei Jia , Jiawei Du , Hui Wei , Jun Chen , Joey Tianyi Zhou , Zheng Wang

An effective reward model plays a pivotal role in reinforcement learning for post-training enhancement of visual generative models. However, current approaches of reward modeling suffer from implementation complexity due to their reliance…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Runtao Liu , Jiahao Zhan , Yingqing He , Chen Wei , Alan Yuille , Qifeng Chen

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…

人工智能 · 计算机科学 2024-10-04 Zeyang Liu , Xinrui Yang , Shiguang Sun , Long Qian , Lipeng Wan , Xingyu Chen , Xuguang Lan

While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workflows remain largely underexplored. To bridge this gap, we introduce Cutverse, a benchmark…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Haobo Hu , Xiangwu Guo , Zhiheng Chen , Difei Gao , Haotian Liu , Libiao Jin , Qi Mao