π Hi, I am Junting Lu (Aidan Lew), currently a second-year master student at Institute for Software Engineering, Peking University (PKU). Prior to that, I received the B.S. degree from Northwestern Polytechnical University (NWPU) in 2023.
π I am currently on the job market!
My current research interests primarily focus on:
- Tool Learning: Explore how to endow large models with human-level tool use abilities.
- OS Agent: Develop intelligent agents that utilize (multi-modal) large language models ((M)LLMs) to operate within operating systems (OS) environments.
- Native VLM Agent: Advancing research on equipping MLLMs with hybird Agent abilities.
π Educations
- [2023.09-2026.06] M.S. Peking University (PKU)
- [2019.09-2023.06] B.S. Northwestern Polytechnical University (NWPU)
π₯ News
- π [2025.09.04]: Weβre excited to announce the release the UI-TARS-2, which is a major upgrade from UI-TARS-1.5, featuring with enhanced capabilities in GUI, Game, Code and Tool Use. It is an βAll In Oneβ Agent model, enabling seamless integration of multiple abilities for complex tasks. Please check our new technical report for more details. Refer to more fantastic showcases at our website.
- π [2025.08.21] 2 papers been accepted by EMNLP 2025.
- π [2025.07.21] LAM been accepted by TMLR 2025.
- π [2025.05.16] AXIS been accepted by ACL 2025.
- π [2025.04.16]: We shared the latest progress of the UI-TARS-1.5 model in our blog, which excels in playing games and performing GUI tasks, and we open-sourced the UI-TARS-1.5-7B.
- π₯ [2025.02.22] We released EasyR1 πππ, an Efficient, Scalable, Multi-Modality RL Training Framework based on veRL.
- π₯ [2024.12.13] We released the UFO v1.2.0 with the code and sample data for Large Action Model (LAM) data collection! Please checkout our new paper and documentation for more details.
- π₯ [2024.07.04] Nissist been accepted by ECAI 2024.
- π [2023.11.23] We released the XAgent v1.0.0! πππ
π Projects
- UI-TARS: An open-source multimodal agent built upon a powerful vision-language model.
- XAgent: An Autonomous Agent for Complex Task Solving.
- UFO: A UI-Focused Agent for Windows OS Interaction.
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL.
π Publications
- UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
UI-TARS Team
Technical Report 2025, [Paper], - Seed1.5-VL Technical Report
Seed VLM Team
Technical Report 2025, [Paper] - AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
Junting Lu*, Zhiyang Zhang*, Fangkai Yang, Jue Zhang, Lu Wang, Chao Du, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
ACL 2025 Main, [Paper] - Large Action Models: From Inception to Implementation
Lu Wang*, Fangkai Yang*, Chaoyun Zhang*, Junting Lu, Jiaxu Qian, Shilin He, Pu Zhao, Bo Qiao, Ray Huang, Si Qin, Qisheng Su, Jiayi Ye, Yudi Zhang, Jian-Guang Lou, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
TMLR 2025, [Paper] - Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
EMNLP 2025, [Paper] - Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides
Kaikai An, Fangkai Yang, Junting Lu, Liqun Li, Zhixing Ren, Hao Huang, Lu Wang, Pu Zhao, Yu Kang, Hua Ding, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
ECAI 2024, [Paper] - PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models
Chenzhuo Zhao*, Ziqian Liu*, Xingda Wang, Junting Lu, Chaoyi Ruan
EMNLP 2025, [Paper] - Code-vision: Evaluating multimodal llms logic understanding and code generation capabilities
Hanbin Wang*, Xiaoxuan Zhou*, Zhipeng Xu, Keyuan Cheng, Yuxin Zuo, Kai Tian, Jingwei Song, Junting Lu, Wenhui Hu, Xueyang Liu
Preprint 2025, [Paper] - TASE: Token Awareness and Structured Evaluation for Multilingual Language Models
Chenzhuo Zhao*, Xinda Wang*, Yue Huang, Junting Lu, Ziqian Liu
Preprint 2025, [Paper]
π Honors and Awards
- [2024] Luo Yuehua Scholarship at Peking University
- [2023] Shaanxi Province Outstanding Undergraduate at NWPU
- [2022] Huawei Scholarship at NWPU
- [2020,2021,2022] National Scholarship for Undergraduate at NWPU
π» Internships
- [2025.2-present] Bytedance-Seed (supervised by Dr. Yujia Qin)
- [2024.3-2024.10] Microsoft DKI Group (supervised by Dr. Fangkai Yang)
- [2023.8-2024.2] ModelBest && TsinghuaNLP (supervised by Dr. Yinxu Pan, Prof. Zhiyuan Liu)
π‘ Lifestyle
- My hobbies include but are not limited to π€singing, πΈguitar, π§ magic and π« bean.