Rishit Dagli

Portrait of Rishit Dagli Portrait of Rishit Dagli

I am interested in learning algorithms, computer vision, graphics and math. My work builds models that can produce physically realistic dynamic worlds as well as understand/ interact with our world.

Currently, I’m a research intern at and a 1st year PhD student at UofT University of Toronto with Sanja Fidler and David I.W. Levin.

I was an undergrad CS/ Math student at UofT University of Toronto. I took a 1-year break from my undergrad to work at as a research intern on AI/ vision/ robotics. During undergrad, I was a research intern at AI Research on video-audio-language models (VLMs). I was also a research engineering intern at a startup on improving inference of multimodal models.

selected publications

  1. Squeeze3D: Extreme Neural Compression with Latent Space Bridging

    Rishit Dagli, Yushi Guan, Sankeerth Durvasula, Mohammadreza Mofayezi, Nandita Vijaykumar
    TMLR 2026
    Project Webpage Abs arXiv

  2. Adaptive Volumetric Mechanical Property Fields Invariant to Resolution

    Rishit Dagli, Donglai Xiang, Vismay Modi, Xuning Yang, Gavriel State, David I.W. Levin, Maria Shugrina
    ICML 2026
    Project Webpage Abs arXiv X/Twitter

  3. RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

    Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, Jonathan Tremblay
    RSS 2026 (Oral)
    Project Webpage Abs arXiv X/Twitter
    press:NVIDIA BlogNVIDIA RoboticsNVIDIA Technical Blog

  4. FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes

    Donglai Xiang*, Vismay Modi*, Rishit Dagli, Ty Trusty, Gilles Daviet, Anka He Chen, Nicholas Sharp, David I.W. Levin
    CVPR 2026 (* joint first authors)
    Project Webpage Abs arXiv X/Twitter
    press:SIGGRAPH Hands-On Lab
  6. Can Vision-Language Models Answer Face to Face Questions in the Real-World?

    Can Vision-Language Models Answer Face to Face Questions in the Real-World?

    Reza Pourreza*, Rishit Dagli*, Apratim Bhattacharyya, Sunny Panchal, Guillaume Berger, Roland Memisevic
    ICLR 2026 (* joint first authors)
    Project Webpage Abs arXiv CVPR Challenge X/Twitter
    press:Thinking Machines Lab

  7. SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound

    Rishit Dagli, Shivesh Prakash, Robert Wu, Houman Khosravani
    SIGGRAPH Posters 2025
    Project Webpage Abs arXiv X/Twitter

teaching