Sign in

Anirvan Sengupta

@anirvansengupta.bsky.social
33 followers 41 following 4 posts

Professor of Physics and Astronomy, Rutgers | Senior Research Scientist, Flatiron Institute | Interested in AI, Neuroscience, Quantum Physics

PostsRepliesMedia
Anirvan Sengupta @anirvansengupta.bsky.social · 29/09/2026
Excited to share that our paper, “Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics”, has been accepted to NeurIPS 2026! Work done with Matt Smart, Soumya Ganguly, Nilava Metya and Alexandre Morozov (@alexm2.bsky.social). arXiv: arxiv.org/pdf/2604.21978
arxiv.org
020
Reposted by Anirvan Sengupta
Cengiz Pehlevan @cpehlevan.bsky.social · 11/07/2025
Great to see this one finally out in PNAS! Asymptotic theory of in-context learning by linear attention www.pnas.org/doi/10.1073/... Many thanks to my amazing co-authors Yue Lu, Mary Letey, Jacob Zavatone-Veth @jzv.bsky.social and Anindita Maiti!
pnas.org
Asymptotic theory of in-context learning by linear attention | PNAS
Transformers have a remarkable ability to learn and execute tasks based on examples provided within the input itself, without explicit prior traini...
1235
Anirvan Sengupta @anirvansengupta.bsky.social · 16/07/2025
At #ICML2025, presenting work done at @flatironinstitute.org w Matt Smart and @albertobietti.bsky.social on in-context denoising (arxiv.org/abs/2502.05164). Come to Matt’s oral, Thursday, 4:15-4:30 PM, West Ballroom A, and see us right after at poster #E-3207, 4:30-7:00 PM, East Exhibition Hall A-B.
arxiv.org
In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
We introduce in-context denoising, a task that refines the connection between attention-based architectures and dense associative memory (DAM) networks, also known as modern Hopfield networks. Using a...
053
Anirvan Sengupta @anirvansengupta.bsky.social · 27/04/2025
Come hear Matt Smart's talk about in-context denoising with transformers at the Associative memory workshop #ICLR25, 2:15pm! This task refines the connection between transformers and associative memories. w/ M Smart and @albertobietti.bsky.social at @flatironinstitute.org
031
Reposted by Anirvan Sengupta
Jacob Zavatone-Veth @jzv.bsky.social · 16/12/2024
The official ad for this postdoc position is now (finally) live, see academicpositions.harvard.edu/postings/14486!
academicpositions.harvard.edu
Postdoctoral Fellow in Theoretical & Computational Neuroscience
Postdoctoral positions are available in Jacob Zavatone-Veth’s research group at Harvard's Center for Brain Science. We are broadly interested in the theory of neural computation; see jzv.io for more i...
2105
Anirvan Sengupta @anirvansengupta.bsky.social · 09/12/2024
Excited to share our work on ‘Deep Learning Based Superconductivity Prediction and Experimental Tests’ at the #NeurIPS2024 workshop on Machine Learning and Physical Sciences ml4physicalsciences.github.io/2024/files/N...
ml4physicalsciences.github.io
040