avatar

Yi Lu

Master Student
Department of Computer Science, University of Toronto
tomlu@cs.toronto.edu


About Me

I am a current Master student (Master of Science in Applied Computing programme) at the University of Toronto. My research interests lies broadly in Multi-Modal Language Model, Reinforcement Learning, Agentic MLLMs and Generative AI.

I am currently working as a full-time co-op applied research intern at ModiFace (L’Oréal’s AI Lab) focusing on controllable video generation. I am also working as a part-time research intern in TIGER Lab under the supervision of Prof. Wenhu Chen, working on a project focusing on Agentic-RL based Tool-calling LLMs. Prior to that, I worked as an research intern at Opus AI Research, where I publiched two papers in top conferences.

I am actively seeking research collaborations and research internship opportunities in MLLM Post Training, Multimodality RL and Controllable Image/Video Generation.

🎓 I’m currently looking for a PhD position starting from 2026 fall in Hong Kong or the US. Feel free to contact me regarding any related opportunities. Here is my resume.

Research Interests

News

  • Oct. 2025
    🔥 VerlTool has reached 600+ stars on Github. It's becoming a key infrastructure for Tool-Augmented Agent RL Post Training.
  • Sep. 2025
    🎉 One paper accepted at NeurIPS 2025 NextVid Workshop.
  • Aug. 2025
    🤫 VerlTool's tech report (co-first author) is released.
  • Jul. 2025
    🏆 Achieved #1 on Multilingual Video Reasoning Evaluation Challenge @CVPR 2025.
  • May. 2025
    🎉 One paper is accepted by ACL 2025.
  • Feb. 2025
    🎉 One paper is accepted by CVPR 2025.
  • Dec. 2024
    🎉 One paper is accepted by AAAI 2025.
  • Oct. 2024
    🏆 Achieved #1 on Long-Term VideoQA Challenge of LOVEU Workshop @CVPR 2024.

Publications

  1. arXiv
    VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
    Dongfu Jiang*, Yi Lu*, Zhuofeng Li*, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, Tianyu Pang, Wenhu Chen
    In Submission
    PDF Code 600+ ⭐ on GitHub

  2. ACL
    RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought
    Yi Lu*, Jiawang Cao*, Yongliang Wu*, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu
    Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
    PDF Main Conference

  3. CVPR
    VEU-Bench: Towards Comprehensive Understanding of Video Editing
    Bozheng Li, Yongliang Wu*, Yi Lu*, Jiashuo Yu, Licheng Tang, Jiawang Cao, Wenqing Zhu, Yuyang Sun, Jay Wu, Wenbo Zhu
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    PDF Highlight

  4. AAAI
    Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark
    Yongliang Wu*, Wenbo Zhu*, Jiawang Cao*, Yi Lu, Bozheng Li, Weiheng Chi, Zihan Qiu, Lirian Su, Haolin Zheng, Jay Wu, Xu Yang
    AAAI Conference on Artificial Intelligence (AAAI), 2025.
    PDF Code

Experiences

  • Research Intern @ TIGER Lab @ University of Waterloo
    Mar. 2025 - Present
  • Applied Research Intern @ ModiFace (L'Oréal's AI Lab)
    May. 2025 - Present
  • Applied Research Intern @ Opus AI Research
    Jan. 2025 - May. 2025
  • Machine Learning Engineer @ OpusClip
    Apr. 2024 - Jan. 2025
  • Data Scientist Intern @ ByteDance
    Aug. 2023 - Dec. 2023

Services

Conference Reviewers


Last Updated: October 2025


Powered by Jekyll and Minimal Light theme.