paper-with-me

홈 › Papers

\textsc{GUI-Spotlight}: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding

2025-10-05 · Bin Lei, Nuo Xu, Ali Payani, Mingyi Hong, Chunhua Liao, Yu Cao, Caiwen Ding arxiv

Multimodal large language models (MLLMs) have markedly expanded the competence of graphical user-interface (GUI) systems, propelling them beyond controlled simulations into complex, real-world environments across diverse platforms. However, practical usefulness is still bounded by the reliability of visual grounding, i.e., mapping textual references to exact on-screen elements. This limitation prevents the system from accurately performing pointer-level actions such as clicking or dragging. To address it, we introduce GUI-Spotlight -- a model trained for image-grounded reasoning that dynamically invokes multiple specialized tools to iteratively narrow its focus to the relevant region of the screen, thereby substantially improving visual grounding accuracy. On the ScreenSpot-Pro benchmark, GUI-Spotlight trained with only 18.5K training samples achieves 52.8\% accuracy, surpassing V2P-7B (50.6\% with 9.6M training samples) and GTA-1-7B (50.1\% with 1.56M training samples).

📄 PDF Abstract BibTeX arXiv:2510.04039

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

ATRIA: Adaptive Traceable ECG Reporting with Iterative Agents

2026-06-23 · Donggyun Hong, Kyuhwan Lee, Junmyung Kwon, Yong-Yeon Jo arxiv

Existing ECG report generation is tightly coupled -- interpretation and reporting fused end-to-end, so errors propagate without stage-level recourse -- while agent-based systems decouple tasks but remain single-pass, nev…

IterLara: A Turing Complete Algebra for Big Data, AI, Scientific Computing, and Database

2023-07-17 · Hongxiao Li, Wanling Gao, Lei Wang, Jianfeng Zhan

\textsc{Lara} is a key-value algebra that aims at unifying linear and relational algebra with three types of operation abstraction. The study of \textsc{Lara}'s expressive ability reports that it can represent relational…

ToolACE-R: Tool Learning with Adaptive Self-Refinement

2025-04-02 · Xingshan Zeng, Weiwen Liu, Xu Huang, Zezhong Wang 외

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, current approaches primaril…

Computational Efficiency

LESS Is More: Mutual-Stability Sampling for Diffusion Language Models

2026-06-15 · Amr Mohamed, Guokan Shang, Michalis Vazirgiannis arxiv

Diffusion large language models (dLLMs) offer a promising alternative to autoregressive decoding by iteratively refining masked sequences, enabling parallel token updates and bidirectional conditioning. Their practical e…

General Knowledge

HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization

2026-08-21 · Jinghao Wang, Qiqi Gu, Chenpeng Wu, Jianguo Yao 외 arxiv

High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolves rapidly, developing efficient methods for automated GPU kernel genera…