Jack Lu

me.jpeg

I’m a third-year Computer Science Ph.D. student in the CILVR lab at NYU Courant, advised by Mengye Ren and collaborating with Greg Durrett and Seunghoon Hong. My research is supported by the NSERC PGS-D Scholarship. Prior to joining NYU, I received my bachelor’s degree in Computer Science and Mathematics from the University of Waterloo.

I’m currently interested in:

  • LLM Reasoning: understanding and improving how LLMs solve and verify problems that require complex reasoning.
  • Adaptive Models and Agents: efficiently adapting diffusion and language models to out-of-distribution tasks, new knowledge, and dynamic environments.

Previously, I did research and software engineering for autonomous driving and ML for healthcare at NVIDIA, Waabi/Uber-ATG, IBM, and DarwinAI. I was fortunate to have worked with Raquel Urtasun, Sanja Fidler, and Alexander Wong.

I’m happy to discuss collaboration, mentorship, and research in general. You can email me for a virtual or in-person chat. My office is at 60 5th Ave, New York.

news

Jul 07, 2025 Our work, Context Tuning for In-Context Optimization, was accepted by the ICML 2025 Test-Time Adaptation Workshop.
Jul 01, 2024 Our work, ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation, was accepted by ECCV 2024.
Apr 25, 2024 I was selected to receive the NSERC PGS-D Scholarship to support my PhD at NYU.
Jan 29, 2024 Our work, SceneControl: Diffusion for Controllable Traffic Scene Generation, was accepted by ICRA 2024.
Sep 01, 2023 I started my PhD in Computer Science at NYU, advised by Mengye Ren.

selected publications

  1. ICML
    context-tuning.png
    Context Tuning for In-Context Optimization
    Jack LuRyan TeehanZhenbang Yang, and Mengye Ren
    ICML Test-Time Adaptation Workshop , Jul 2025
  2. ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation
    Jack LuRyan Teehan, and Mengye Ren
    European Conference on Computer Vision (ECCV) , Oct 2024
  3. SceneControl: Diffusion for Controllable Traffic Scene Generation
    IEEE International Conference on Robotics and Automation (ICRA) , May 2024
  4. Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression From Chest CT Images
    Frontiers in Artificial Intelligence , Nov 2021