←
Sambit Ghosh4 posts
Sambit Ghosh avatar

Sambit Ghosh

@sambitghsh

IBM Research, IISc, Trustworthy AI

◷ Joined July 2023
Sambit Ghosh avatar
Sambit Ghosh@sambitghsh·Oct 21

Really excited to share this work! We look at a fundamental question in SAE training: How much data do you actually need to train a Sparse Autoencoder (SAE)? Give it a read and let us know what you think!

Exciting work led by @sambitghsh and @MadelynMathai on the diminishing returns of data in Sparse Autoencoders. Standard practice often uses millions of activation tokens, but it’s unclear whether that scale is necessary for different SAE goals. We investigate this systematically by training different SAE architectures on different LLM families with training budgets ranging from 5M to 500M activation tokens.

Post attachment
Chirag Agarwal avatar
⟳ Sambit Ghosh retweeted
Chirag Agarwal@_cagarwal·Jun 9

We are thrilled to announce the inaugural Agyeya Research Workshop, hosted in partnership with the @iiscbangalore! Our mission is to break down barriers for early-career researchers and cultivate India’s next generation of AI leaders. As part of the workshop, we are also launching the Agyeya AI Scholar program. This initiative aims to select and train a dedicated cohort of candidates through hands-on research and mentorship in AI Alignment, Interpretability, and Safety. 🗓️ Apply by June 30th and stay tuned for our upcoming mentor announcements! Find more details and submit your application here: lnkd.in/efGa44KT @ponguru Sriparna Saha, @rvbabuiisc, @NikitaKharya, @precogatiiith @val_iisc

Vision and AI Lab, IISc avatar
⟳ Sambit Ghosh retweeted
Vision and AI Lab, IISc@val_iisc·Jun 5

📣Thrilled that "Rethinking Dataset Distillation: Hard Truths about Soft Labels" is a Best Paper Finalist @CVPR (Top 15 out of 16,000+ submissions)! 🏆 Congrats to the authors! 🥳🙌🏻 Join us today: 🎙️ Oral: 10:15 @ Mile High Ballroom 1A-2A 📍Poster 18 @ ExHall A

Chirag Agarwal avatar
⟳ Sambit Ghosh retweeted
Chirag Agarwal@_cagarwal·May 27

Do Vision Language Models (VLMs) really need deep visual processing? 🤖 Our paper accepted as Oral Presentation @CVPR TRUE-V Workshop suggests the current paradigm of multimodal LLM architectures might be wildly inefficient. Here is why we might be over-processing image tokens 🧵 (1/4) Paper: arxiv.org/abs/2604.09425 Code: github.com/sambitghsh/VLM-To… Congrats to @sambitghsh for leading this work! Great collaboration with @rvbabuiisc and @val_iisc!

Post attachment