bofei.jpg

Bofei Zhang (张博飞)

Email: zhangbofei5675[at]outlook[dot]com

Experience

Career

  • 2025/7-Current; Researcher @ Tiktok AIIC(AI创新中心)
    • Working on SFT & RL for GUI Agent
  • 2023/3-2025/7; Research Engineer @ Beijing Institute for General Artificial Intelligence (BIGAI)
    • Worked on Vision Language Model & Agentic Task Post-Training.
  • 2020/6-2023/3; Software Engineer @ ByteDance
    • Tiktok & Lark

🚀 Job Referral(职位内推)Available — Details here →

如果你需要工业级基准数据集,请联系 GADE Union

Education

  • 2018/9-2020/6; Master in Data Science @ New York University
  • 2013/8-2018/5; Bachelor in Biomedical Engineering @ The Ohio State University


News

Aug 21, 2026 Our paper Fully Decoupled Reinforcement Learning with Adaptive Data Curation for GUI Agents (DART-GUI) has been accepted to the EMNLP 2026 Main Conference! 🎉
Nov 13, 2025 TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials is accepted by AAAI 2026! 🎉; Checkout detail for this project here!
Dynamic JSON Badge Dynamic JSON Badge Dynamic JSON Badge Dynamic JSON Badge
Sep 26, 2025 Our paper “Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning” has been accepted by NeurIPS 2025! 🎉
Feb 07, 2025 Multi-modal Agent Tuning (MAT): A framework for auto-generating multimodal tool-usage trajectories (20K MM-Traj), boosting MiniCPM & Qwen-VL tool use by 20%. This work is accepted by ICLR 2025!
Aug 02, 2024 Introducing 🔥FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models. Checkout Here for more details! 🔥FIRE are accepted by NeurIPS 2024!

Latest Posts

Selected Publications

* Equal contribution, ✉ Corresponding author

  1. dart-gui.png
    Fully Decoupled Reinforcement Learning with Adaptive Data Curation for GUI Agents
    Pengxiang Li , Zechen Hu , Zirui Shang, and 15 more authors
    Annual Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
  2. cof.jpg
    Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL
    Xintong Zhang* , Zhi Gao* , Bofei Zhang, and 8 more authors
    Preprint, 2025
  3. sport.jpg
    Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
    Pengxiang Li* , Zhi Gao* , Bofei Zhang, and 8 more authors
    Advances in Neural Information Processing Systems (NeurIPS), 2025
  4. tongui.png
    TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials
    Bofei Zhang* , Zirui Shang* , Zhi Gao*, and 7 more authors
    AAAI Conference on Artificial Intelligence (AAAI), 2026
  5. mat.png
    Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage Spotlight (Top 5%)
    Zhi Gao* , Bofei Zhang* , Pengxiang Li*, and 7 more authors
    International Conference on Learning Representations (ICLR), 2025
  6. 2024fire.png
    FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
    Pengxiang Li* , Zhi Gao* , Bofei Zhang*, and 6 more authors
    Neural Information Processing Systems: Datasets and Benchmarks (NeurIPS D&B), 2024