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
🚀 Referral(内推) Available — Details here →
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
| Oct 03, 2025 | New preprint: Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation (DART-GUI).
If you find this research helpful, consider starring the GitHub repo and upvoting the HF paper page. |
|---|---|
| Sep 26, 2025 | Our paper “Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning” has been accepted by NeurIPS 2025! 🎉 |
| Apr 19, 2025 | Release dataset, model and training & evaluation code for TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials |
| 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
| Aug 08, 2025 | ByteDance Referral |
|---|---|
| Jun 14, 2025 | Computer-Use MacOS Agent |
| Feb 07, 2025 | Tutorial of training Multi-modal Agent Tuning projects with LLaMA-Factory |
Selected Publications
* Equal contribution, ✉ Corresponding author