Rishit Dagli

CS, Math, Stats Undergrad at UofT, DGP Lab, Vector Institute

rishit.png rishit.png

I am mainly interested in learning algorithms, computer vision (visual generation, vision-language models, and neural rendering), learning theory, and math. I have also represented my country in international olympiads. Feel free to talk with me about anything CS, Math, Robotics, or Physics.

I have had the pleasure of working with many awesome people at the University of Toronto. After I switched boats to research I have worked in industry at Qualcomm AI Research with Roland Memisevic and Guillaume Berger and at Civo with Josh Mesout.

In a past life, I used to work on software engineering and robotics. I contribute extensively to/ maintain popular open-source projects like TensorFlow, PyTorch Foundation, Kubernetes, Kubeflow, PapersWithCode, freeCodeCamp among others. I still work on building a few open-source projects, some of which have been pretty popular. Seeing my work at a rather young age, I was invited to speak at 2 TEDx and 1 TED-Ed events.

news

Oct 3, 2024 We released a new large-scale dataset for video understanding. Arxiv. Dataset. (code release soon, in the hands of corporate overlords)
Feb 13, 2024 Received the T-CAIREM award for students at UofT.
Jun 18, 2023 We released the first vision (images and video)-spatial audio model as a step towards complete generation. Arxiv. Code and Web Demo.

selected publications

  1. airletters.png
    AirLetters: An Open Video Dataset of Characters Drawn in the Air
    Rishit Dagli, Guillaume Berger, Joanna Materzynska, and 2 more authors
    ECCVW 2024
  2. nerfus.png
    NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild
    Rishit DagliAtsuhiro HibiRahul G. Krishnan, and 1 more author
    PMLR 2024
  3. s2s.png
    SEE-2-SOUND custom_emoji : Zero-Shot Spatial Environment-to-Spatial Sound
    Rishit DagliShivesh PrakashRobert Wu, and 1 more author
    ICMLW 2024
  4. finch.png
    Beyond the Visible: Jointly Attending to Spectral and Spatial Dimensions with HSI-Diffusion for the FINCH Spacecraft
    Ian VyseRishit DagliDav Vrat Chadha, and 26 more authors
    SSC 2024 (Oral)
  5. diffuseraw.jpg
    DiffuseRAW: End-to-End Generative RAW Image Processing for Low-Light Images
    Rishit Dagli
    arXiv preprint arXiv:2402.18575 2023
  6. truck_mnerf.png
    PyTorch Made Efficient for the Edge: WASI-NN
    Rishit Dagli, and Shivay Lamba
    PyTorch Conference 2023