I am a computer science undergraduate at Xi'an Jiaotong University and a member of the AI Empowerment Pilot Class. My research interests include multimodal perception and AI agents and reinforcement learning.

๐Ÿ”ฅ News

  • 2026.08: MacAgentBench was accepted to EMNLP 2026 as Oral! (Co-first author)
  • 2026.06: CVSBench was accepted to ECCV 2026.
  • 2026.02: ZoomEarth was accepted to CVPR 2026 as a Highlight! (Co-first author)

๐Ÿ“ Publications

* denotes equal contribution; † denotes corresponding authors.

CVPR 2026 ยท HighlightZoomEarth overview: active perception and multi-scale tools for geospatial vision-language tasks

ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks

Ruixun Liu*, Bowen Fu*, Jiayi Song, Kaiyu Li, Wanchen Li, Lanxuan Xue, Hui Qiao, Weizhan Zhang, Deyu Meng, Xiangyong Cao†

[Paper] [PDF] [Project]

A tool-using vision-language model that actively zooms and revisits high-resolution geospatial imagery, trained with SFT and GRPO.

EMNLP 2026 ยท OralMacAgentBench: GUI and hybrid agents, macOS tasks, and fine-grained checkpoint evaluation

MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop

Yikun Fu*, Bowen Fu*, Zhenyu Wu, Shuang Cheng, Xiaowei Sun, Bowen Yang, Zehao Li, Yibo Zhao, Zichen Ding, Zhoumianze Liu, Shijie Wang†, Biqing Qi†, Bowen Zhou†

[Paper] [PDF] [Project]

A benchmark of 676 realistic macOS tasks for computer-use agents, supporting GUI and CLI interaction with fine-grained checkpoint evaluation.

ECCV 2026CVSBench overview: cross-view spatial reasoning and dreaming tasks

CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming

Ruixun Liu*, Lingyu Zhang*, Lanxuan Xue, Kaiyu Li†, Bowen Fu, Xiangyong Cao†

[Paper] [PDF] [Project]

A comprehensive benchmark for evaluating spatial reasoning and dreaming across different viewpoints.

arxivAARRI-Bench overview: research task creation, agent evaluation, and benchmark highlights

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

Jiayu Wang*, Weijiang Lv*, Bowen Fu*, Jing Fu, Jiayi Song, Lingyu Zhang, Lanxuan Xue, Luodi Chen, Zepeng Xin, Kaiyu Li, Xiangyong Cao†

[Paper] [PDF] [Project]

Evaluating whether research agents can handle the professional judgment and fine-grained decisions involved in real research workflows.

๐Ÿ“– Education

  • Sep. 2023 โ€“ Present, Xi'an Jiaotong University, B.Eng. in Computer Science and Technology.

๐ŸŽ– Honors and Awards