Krishnaswamy Lab

Today, I’m proud to share our latest work published in @NatureBiotech describing MELD, a #MachineLearning algorithm for #SingleCell perturbation analysis. Read this #tweetorial to learn about the work led by @dbburkhardt and Jay Stanley 🥳🎉🧪 nature.com/articles/s4158… (1/16)

📢Yuan Gao and colleagues propose Helix, a deep-learning framework for modeling tissue- and context-specific RNA splicing and isoform usage. nature.com/articles/s4358… 🔓rdcu.be/fjzI5

🫖The Boston TAG Party! 📢No AI without Mathematical Representation! 🌎August 18-20 @ NU, Boston, MA, USA CfP & info: tagds.com/events/tag-ds-… OpenReview: openreview.net/group?id=TAG-D…

@fabian_theis Happy birthday!

50 today 🎉 Feeling a tad older, but mostly very grateful: to family, friends, colleagues, collaborators, and students for the journey so far! Huge thanks to my department for amazing surprise reception today. You certainly know how to celebrate science & aging in style 😄🚀

Congrats to all @YaleCSDept graduates this year! We had students graduating at many levels: @DanqiLiao73090, Dami Fasina, and close collaborator @ericalbusch from their Ph.Ds!! Panos Ketonis and @rishabh16_ from masters, and undergrads @HowardDai82717 Ananya Krishna, Lucas Lee, Kaiden Brown, @BrianDiBassinga and more !

Hello from the top of Glacier 3000 in the Swiss alps! (Yes this is all for science!)

At the Gordon Research conference on single cell genomics ! Amazing lineup including @mariabrbic @jmuiuc @yuefeng_1 @fabian_theis @jure @CarolineUhler Christina Leslie and others. Also spectacular location in the Swiss alps! Thanks for organizing @drAOPisco and Sunny Xie!

Happy to report on our Deep Learning Theory and Applications team (Comp Sci 4520/5520) at Yale! The class 75 students, approx 25 auditors. It featured the gamut of content from SGD to diffusion models to LLMs to NTKs. The raw scores of most of the class was >90%!! The projects ranged from deep learning systems for predicting wildfires, to single cell data, to electric circuit simulations. Exciting stuff! Thanks to my class students and teaching team: @Siddharth2814 Jake Kovalic, @KeXU0828 @XingzhiSun!

Neural networks might speak English, but they think in shapes. Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision. Starting today, we’re releasing a series of posts on this research agenda. 🧵

Talking at the Future of Math Symposium in 10 minutes (livestream link: youtube.com/live/tN4hsT5t0…). I decided to make the talk "personal" and explain the five moments that updated me on how fast AI will change mathematics. (The ChatGPT's illustration of these moments is so good!!)

1/ 🎉 Our paper "HypRAG: Hyperbolic Dense Retrieval for Retrieval-Augmented Generation" has been accepted at ICML 2026! We move dense retrieval out of Euclidean space and into hyperbolic space, and it changes a lot. 🧵

All that “hitting refresh” has paid off! 3 exciting papers accepted! Looking forward to @icmlconf in Korea!

Smita Krishnaswamy (Associate Professor of Genetics and of Computer Science, Yale University) will discuss multimodal #foundationmodels for biomolecular analysis at The Festival of Genomics, Biodata & AI! Register now: hubs.la/Q04dHfBS0 #FOGBoston #AI @KrishnaswamyLab

@thegautamkamath @eatcs_secretary Congrats!

I am honoured (and still a bit stunned) to receive the 2026 Presburger Award from @eatcs_secretary. This recognizes 1 or 2 young scientists for outstanding contributions in theoretical CS This honour is shared w my collaborators, students, institutions, & research community 1/7

Update I will also be at the Panel Discussion at genai-in-genomics.github.io @iclr_conf at 11:30 if you want to discuss stuff with me (and others)!

If you are at @iclr_conf on Monday: I will be talking at @MLGenX about "Learning data-driven structure & dynamics models lab-in-the-loop AI scientists"... key ingredients and recipes for creating AI scientists that model systems from data to generate hypotheses!

@pfau I took pictures like this as proof

Is anyone actually attending ICLR?

🚨Why should one huge LLM know and solve everything? - No single human does, yet our civilization does endless innovation. Introducing AC/DC - it continually coevolves a population of small expert LLMs that collectively outperform GPT-4o. (ICLR 2026 w/ @SakanaAILabs) 👇🧵

Nothing like a hike through the @Tijuca rainforest and a shower in the waterfalls to refresh you @iclr_conf !