Rushil Anirudh

D93CCDC5-529F-4134-A5E8-909F0A40649D


Hi! I am a Computer Scientist with the Machine Intelligence Group at Lawrence Livermore National Laboratory (LLNL), a Federally Funded Research Institute. My research interests broadly include computer vision, machine learning, and high dimensional data analysis.

I’m fortunate to be able to collaborate with scientists and researchers across several areas of science and engineering — for example high energy physics; epidemiology for COVID19; x-ray imaging; human connectome project; healthcare.

I spend a lot of my time thinking about modeling and understanding high dimensional, multi-modal, and inherently structured data. I serve as a reviewer for several top machine learning and computer vision publications (NeurIPS, CVPR, ICLR, ICCV, ICML, AAAI. etc).

I also lead the Open Data Initiative with the goal of releasing LLNL’s high impact scientific datasets for machine learning — so far, we have 9 datasets and counting!

My resume (pdf, updated Jan 2021). Contact:undefined

Updates

  • (Jan 2021) Co-organizing the 6th edition of DiffCVML as a workshop at CVPR 2021.
  • (Jan 2021) ✨✨Our paper on “Generative Patch Priors” won Best Paper Honorable Mention at WACV 2021! Thank you to the organizers and awards committee for recognizing our work! We have released the code on github.
  • (Dec 2020) Two papers accepted to AAAI 2021!:
    • Attribute-Guided Adversarial Training for Robustness to Natural Perturbation led by Tejas. (arXiv) — Studies robustness to semantic shifts that are beyond L-p norm perturbations
    • Accurate and Robust Feature Importance Estimation under Distribution Shifts led by Jay. (arXiv) — Studies ML explainability under distribution shifts
  • (Nov 2020) Two papers accepted to WACV 2021 with Suhas and Pavan:
    • Recovering Trajectories of Unmarked Joints in 3D Human Actions Using Latent Space Optimization (arXiv)
    • Generative Patch Priors for Practical Compressive Image Recovery (arXiv).