Sumedh Hindupur

Namaskaram! (Hello!)

I am Sumedh, a Ph.D. candidate in Applied Mathematics at Harvard University's School of Engineering and Applied Sciences, working under the supervision of Prof. Demba Ba.

I am the co-founder of PRISM, a reading club systematically exploring the similarities and differences between ML interpretability and neuroscience, at Harvard SEAS and the Kempner Institute.

Prior to joining Harvard, I earned a Dual Degree (BTech+MTech) in Electrical Engineering from the Indian Institute of Technology Bombay in August 2023, where I was honored with the Institute Silver Medal for graduating as the Department Topper.
My master's thesis, supervised by Prof. Vivek Borkar, focused on novel approaches for online parameter estimation in Partially Observed Markov Decision Processes (POMDPs).

In my free time, you can find me:
Long distance running: I finally ran a marathon (unofficial) in September 2025 after 6 months of DIY training!
Lawn tennis: I am an officer and former co-President of the Harvard Griffin GSAS Tennis Club, the largest graduate club at Harvard with >250 aggregate members!
Reading novels: Most recently, I finished Antoine de Saint-Exupéry's The Little Prince. It is one of the most beautiful books I've ever read!
"But the eyes are blind. One must look with the heart"

Research Interests

My research lies at the intersection of neural network interpretability, computational neuroscience, and signal processing. I am particularly interested in understanding the internal representations of artificial neural networks and biological brains, by developing tools for interpretability. In my recent work, I have shown that interpretability tools need to be designed using suitable inductive biases about the geometric structure of concepts in deep neural network activations, failing which they will not be able to capture those concepts. With my collaborators, I have demonstrated the importance of inductive biases by constructing suitable tools such as:
SpaDE (Sparsemax Distance Encoder) to capture concepts that are nonlinearly separable and heterogeneous (Hindupur et al, NeurIPS 2025),
Temporal Feature Analyser (TFA) to capture concepts associated with temporal structure, such as new concepts learnt in-context, event boundaries in narrations, parsing of garden-path sentences (Lubana, Rager, Hindupur et al, arXiv 2025)
SparKer (Sparse ensemble of local Kernels) to identify statistical anomalies in data across sciences (particle physics) and ML (word embedding models) (Grosso et al, arXiv 2025)

Publications

"Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies" [paper link]
Gaia Grosso, Sai Sumedh R. Hindupur, Thomas Fel, Samuel Bright-Thonney, Philip Harris, Demba Ba
Preprint on arXiv (2025)
"Priors in Time: Missing Inductive Biases for Language Model Interpretability" [paper link]
Ekdeep Singh Lubana*, Can Rager*, Sai Sumedh R Hindupur*, et al
Published in International Conference on Learning Representations (ICLR) 2026
"Projecting Assumptions: The Duality between Sparse Autoencoders and Concept Geometry" [paper link]
Sai Sumedh R. Hindupur*, Ekdeep Singh Lubana*, Thomas Fel* and Demba Ba
Published in Advances in Neural Information Processing Systems (NeurIPS) 2025
"Population Coding under the Scale-Invariance of High-Dimensional Noise" [paper link]
S. Amin Moosavi, Sai Sumedh R. Hindupur, Hideaki Shimazaki
Preprint on bioRxiv (2024)
"Online Parameter Estimation in Partially Observed Markov Decision Processes" [paper link]
Sai Sumedh R. Hindupur, Vivek S Borkar
Published at the 59th Annual Allerton Conference on Communication, Control, and Computing (2023)

*denotes equal contribution (co-first authors)

Invited Talks/ Seminars

Invited Seminar at Department of Electrical Engineering, IIT Bombay (January 23, 2026)
Invited Speaker at Caltech NeuroAI Journal Club (virtually on Zoom) (May 28, 2025)

Posters

Priors in Time: A Generative View of SAEs for Sequential Representations [link]
at the 2nd New England Mechanistic Interpretability Workshop (NEMI), Northeastern University, Boston, MA (August 22, 2025)
Projecting Assumptions: The Duality between Sparse Autoencoders and Concept Geometry [link]
1. Methods and Opportunities at Small Scale (MOSS) Workshop at ICML 2025, Vancouver, Canada (July 19, 2025)
2. New England NLP Workshop (NENLP), Yale University, New Haven, CT (April 11, 2025)
3. 2nd Spring into Science by the Kempner Institute at Harvard University, Loft on Two, Boston, MA (March 26, 2025)
SPrInt: Sparsemax Prototypes for Interpretability [link]
at the 1st New England Mechanistic Interpretability Workshop (NEMI), Northeastern University, Boston, MA (August 19, 2024)

Prior Work

In my undergrad+masters degree at IIT Bombay, I worked on multiple research projects:

Online parameter estimation in POMDPs [paper] (with Prof. Vivek Borkar, IIT Bombay)
This work introduces a novel methodology for real-time parameter estimation in POMDPs using maximum likelihood estimation integrated with extremum-seeking. The framework enables online learning for sequential decision-making processes with partial observations and is supported by theoretical analyses and extensive numerical validations.
Neural population coding in the mouse visual cortex [paper](in collaboration with Dr. Amin Moosavi, UCLA and Prof. Hideaki Shimazaki, Kyoto University),
This study explores the role of scale-invariant noise structures in high-dimensional neural activity and their implications for population coding. Using large-scale neural recordings from the mouse visual cortex, we identify conditions under which neural populations achieve unbounded information capacity, offering insights into the scalability of neural coding systems.
Spiking neural network architectures [report] (with Prof. Alice Parker, University of Southern California),
We simulated a biologically inspired spiking neural network to tackle catastrophic forgetting in sequential learning tasks. By leveraging mechanisms like dopamine-driven reward learning and synaptic plasticity, the NeuRoBot successfully retained previously learned skills while acquiring new ones. This work bridges neuroscience insights with adaptive AI design.
MEG-based signal analysis of neural activity [report] (with Prof. Ole Jensen and Dr. Yali Pan, University of Birmingham).
We investigated interactions between brain oscillations during reading by analyzing MEG data. Using rapid frequency tagging and statistical tests, we studied subtle interactions between alpha oscillations and high-frequency activity in the visual cortex.

I have an inexplicably long name (thanks mom and dad!), so you might see various versions of it:
Sai Sumedh R. Hindupur (on research publications, google scholar)
Sai Sumedh Hindupur Ravindra (legal)
Sai Sumedh H. R. (linkedin and academic records)
Sumedh Hindupur (on Harvard websites)

I promise it's all just one person (me)!

Page updated

Google Sites

Report abuse