Nishanth Shetty

PhD Student at the Indian Institute of Science.

prof_pic.jpg

Spectrum Lab, C-239

EE, IISc, Bangalore-560012

Hi. I am Nishanth. I am a PhD student in the Department of Electrical Engineering, Indian Institute of Science, Bengaluru, under the supervision of Prof. Chandra Sekhar Seelamantula. The focus of my PhD is understanding sampling from high dimensional distributions in the context of deep generative modelling, in particular, score-based generative models, diffusion models and generative adversarial networks. I’m currently exploring score-matching and its variants with a focus on image generation. On the applied side, I am interested in the potential of using generative models as priors to solve inverse problems in computational imaging. My PhD is graciously funded by the Prime Ministers’ Research Fellowship (PMRF) and Qualcomm Innovation Fellowship 2023, 2024.

Previously, I completed my Bachelors in Electronics and Communication Engineering from PES University, Bangalore.

news

Dec 21, 2024 Monte Carlo Score Matching for Image Generation got accepted at ICASSP 2025, Hyderabad! :tada:
Jul 24, 2024 We won the Qualcomm Innovation Fellowship 2024 for our proposal titled Exploring the Connections Between Brownian Motion and Diffusion Models! :tada:
Dec 14, 2023 MILD: Momentum Imbued Langevin Dynamics got accepted at ICASSP 2024, Seoul! :tada:
Oct 27, 2023 f-GANs Settle Scores! got accepted in the NeurIPS 2023 Workshop on Diffusion Models. A big shout-out to my co-authors! :tada:
Jun 30, 2023 Kartheek and I won the Qualcomm Innovation Fellowship 2023 for our proposal titled Compressed Generative Models on Data Manifolds! :tada:

selected publications

  1. Monte Carlo Score Matching for Image Generation
    Nishanth Shetty, and Chandra Sekhar Seelamantula
    In Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2025
  2. MILD: Momentum Imbued Langevin Dynamics for Faster Sampling
    Nishanth Shetty, Manikanta Bandla, Nishit Neema, Siddarth Asokan, and Chandra Sekhar Seelamantula
    In Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2024
  3. f-GANs Settle Scores!
    Siddarth Asokan, Nishanth Shetty, Aadithya Srikanth, and Chandra Sekhar Seelamantula
    In NeurIPS 2023 Workshop on Diffusion Models, 2023