collaborators

11 papers

cs.AI2026

Scaling GUI Agents with Visual State Transitions

Xiangyan Liu, Kaixin Li, Haonan Wang +6

We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal model on visual state trans…

cs.CL2026

I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications

Dasen Dai, Biao Wu, Meng Fang +2

Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly trans…

cs.CL2026

PaperVoyager : Building Interactive Web with Visual Language Models

Dasen Dai, Biao Wu, Meng Fang +1

Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly trans…

cs.CV2026

DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models

Biao Wu, Yiwu Zhong, Meng Fang +1

High-quality and diverse multimodal data are essential for improving vision-language models (VLMs), yet existing datasets often contain noisy, redundant, and poorly aligned samples…

cs.CV2026

VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery

Jinchao Ge, Tengfei Cheng, Biao Wu +7

Understanding cultural heritage artifacts such as ancient Greek pottery requires expert-level reasoning that remains challenging for current MLLMs due to limited domain-specific da…

cs.CV2025

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

Baode Wang, Biao Wu, Weizhen Li +8

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer fr…