7 papers
Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes
Yifan Jiang, Cong Zhang, Bofei Zhang +4
Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy ove…
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
Pengxiang Li, Zhi Gao, Bofei Zhang +8
Multimodal agents, which integrate a controller e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks.…
Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
Xintong Zhang, Zhi Gao, Bofei Zhang +8
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks. However, the multimodal reasoning capability has not been fully explor…
TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
Bofei Zhang, Zirui Shang, Zhi Gao +7
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. Ho…
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Pengxiang Li, Zechen Hu, Zirui Shang +15
Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL):…
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
Zhi Gao, Bofei Zhang, Pengxiang Li +7
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to so…