Sahil Verma

PhD student @uwcse. Robustness and Interpretability. Currently at @MSFTResearch. Former intern at @amazon, @itsArthurAI. Undergrad @IITKanpur

[Sahil Verma @Sahil1V]

@liujc1998 Congratulations!

[Sahil Verma @Sahil1V]

@thsottiaux thank you!

[Arnav Das @arnaved]

Thrilled to present our paper: Matched Data, Better Models: Target Aligned Data Filtering with Sparse Autoencoders at ICLR today 🎉! We use SAEs to filter pretraining datasets for CLIP-style models.
📍 Poster Session 6, Pavilion 4 | 3:15–5:45pm today
📄 https://t.co/a7yyHn0MR7

[Sahil Verma @Sahil1V]

@Yuchenj_UW yeah but clear is like just starting a new session, so why not do that? I agree with compact

[Sahil Verma @Sahil1V]

@olliezliu @reflection_ai Congratulations!

[Sahil Verma @Sahil1V]

@forwarddeploy would love to join!

[Sahil Verma @Sahil1V]

@hazhubble @butcher_jasper

[Sahil Verma @Sahil1V]

@Yuchenj_UW where do you find about these meetups?

[Sahil Verma @Sahil1V]

@ArmenAgha 100%, thank you

[Sahil Verma @Sahil1V]

@reach_vb @sama Unfortunately it doesn't work with remote ssh server code, would that change soon?

[Sahil Verma @Sahil1V]

@Tim_Dettmers This is so good, Tim. Very interesting that you read about Krishna and Arjuna!

[Sahil Verma @Sahil1V]

@paraschopra @lossfunk @butcher_jasper

[Soumye Singhal @soumyesinghal]

🚀 Nemotron 3 Nano is live! Had a blast post-training this model with a cracked team. Its strong for its size, and highly efficient at inference.

And true to @nvidia's open release style: weights (BF16/FP8/base) + training recipes + code + datasets.

HF: https://t.co/IE7OCOU2qd
Blog + Nano tech report: https://t.co/Qioq9N2ewg

[Sahil Verma @Sahil1V]

@liweijianglw You are leaving a real heritage @liweijianglw!

[Sahil Verma @Sahil1V]

@r_krishna3 @naturemethods Congratulations @r_krishna3 and @butcher_jasper

[Rohith Krishna @r_krishna3]

Today, we report a method for design of active enzymes, RFdiffusion2, in @naturemethods. For the first time, we are able to design enzymes with native-range catalytic activity.
We also are releasing our next frontier model, RFdiffusion3, code 👇

[Sahil Verma @Sahil1V]

Sarah is great, go work with her!

[Sarah Wiegreffe @sarahwiegreffe]

I am recruiting 2 PhD students to work on LM interpretability at UMD @umdcs starting in fall 2026!

We are #3 in AI and #4 in NLP research on @CSrankings.
Come join us in our lovely building just a few miles from Washington, D.C. Details in 🧵

[Divyat Mahajan @divyat09]

[1/9] While pretraining data might be hitting a wall, novel methods for modeling it are just getting started!

We introduce future summary prediction (FSP), where the model predicts future sequence embeddings to reduce teacher forcing & shortcut learning.

📌Predict a learned embedding of the future sequence, not the tokens themselves

[Sahil Verma @Sahil1V]

Hands down Hila is one of the best advisors out there, you would be lucky to work with her! (as was I :) )

[Hila Gonen @hila_gonen]

Considering a PhD/MSc in NLP?
I’m hiring students this cycle!
If you are passionate about making language models reliable and safe, eager about understanding and controlling language models, and would like to add to your research some multilingual flavor - apply to my group! 👇

[Jasper Butcher @butcher_jasper]

Very excited to share our paper "De novo Design of All-atom Biomolecular Interactions with RFdiffusion3", now on BioRXiv. https://t.co/ry7b17DHgy 1/n