Nishanth Shetty
PhD Student at the Indian Institute of Science.
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. My research focuses on the mathematics of sampling from high-dimensional distributions in the context of score-based generative models and their connections to stochastic differential equations, Langevin dynamics, and optimal control. I am also interested in applying these ideas to inverse problems in imaging and signal processing. I’m currently exploring score-matching and its variants with a focus on image generation. My PhD is graciously funded by the Prime Minister’s Research Fellowship (PMRF) and the Qualcomm Innovation Fellowship 2023 and 2024.
Previously, I pursued my undergraduate studies as a Bachelor of Technology student in the department of Electronics and Communication Engineering from PES University, Bangalore.
news
| May 14, 2026 | Recognized as a Gold Reviewer for ICML 2026!  |
|---|---|
| May 13, 2026 | Received the outstanding teaching assistant award from the Department of Electrical Engineering! |
| Oct 3, 2025 | New preprint out on arxiv - Dale meets Langevin: A Multiplicative Denoising Diffusion Model! |
| Dec 21, 2024 | Monte Carlo Score Matching for Image Generation got accepted at ICASSP 2025, Hyderabad! |
| Jul 24, 2024 | We won the Qualcomm Innovation Fellowship 2024 for our proposal titled Exploring the Connections Between Brownian Motion and Diffusion Models! |
selected publications
- Monte Carlo Score Matching for Image GenerationIn Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2025
- MILD: Momentum Imbued Langevin Dynamics for Faster SamplingIn Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2024
- f-GANs Settle Scores!In NeurIPS 2023 Workshop on Diffusion Models, 2023