5 papers
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
Dingming Li, Hongxing Li, Zixuan Wang +9
Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring c…
A Survey on (M)LLM-Based GUI Agents
Fei Tang, Haolei Xu, Hang Zhang +12
Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction, evolving from rule-based automation scripts to sophisticated AI-drive…
SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
Siqi Chen, Xinyu Dong, Haolei Xu +10
Large Language Models (LLMs) and Multimodal LLMs have shown promising capabilities for SVG processing, yet existing benchmarks suffer from limited real-world coverage, lack of comp…
Generalized Visual Relation Detection with Diffusion Models
Kaifeng Gao, Siqi Chen, Hanwang Zhang +3
Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance,…
Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
Fei Tang, Yongliang Shen, Hang Zhang +7
Humans can flexibly switch between different modes of thinking based on task complexity: from rapid intuitive judgments to in-depth analytical understanding. However, current Graph…