Excited to share a new framework to design provably efficient inverse reinforcement learning algorithms, to appear at #ICML2024. Special thanks to all my collaborator, especially Gokul Swamy for his incredible mentorship! Check out his tweet for more info! x.com/g_k_swamy/stat…

It’s an honor to have been named a “rising star” by Stanford in management science and engineering, and to be featured on the Cornell Tech website :)

1 down, N-1 to go… Moving from Ithaca to NYC today, which marks the end of my first year as a PhD student! This year in Ithaca has been full of wonderful friends and lots of growth :) Excited for the rest! 🌃

My NSF CAREER proposal was just awarded! Excited to continue our work on data science/AI/operations for the public interest, especially w/ govt agencies to reduce disparities. Thankful to my students/mentors/collaborators Cornell Tech Cornell University Stanford University and beyond!

Please retweet: I am recruiting PhD students at Berkeley! Please apply to UC Berkeley EECS or UC Joint Computational Precision Health Program if you are interested in ML applied to health, inequality, or social science, and mention my name in your app. More details on work/how to apply: cs.cornell.edu/~emmapierson/

💡New preprint & Python package: We use sparse autoencoders to generate hypotheses from large text datasets. Our method, HypotheSAEs, produces interpretable text features that predict a target variable, e.g. features in news headlines that predict engagement. 🧵1/

New paper/code! Sparse Autoencoders for Hypothesis Generation HypotheSAEs generates interpretable features of text data that predict a target variable: What features predict clicks from headlines / party from congressional speech / rating from Yelp review? Our method has three

check out the findings from our #dogathon 😍🐶 !!

The US government recently flagged my scientific grant in its "woke DEI database". Many people have asked me what I will do. My answer today in nature. We will not be cowed. We will keep using AI to build a fairer, healthier world. nature.com/articles/d4158…

I’m stoked to share our new paper: “Harnessing the Universal Geometry of Embeddings” with jack morris, Collin Zhang, and Vitaly Shmatikov. We present the first method to translate text embeddings across different spaces without any paired data or encoders. Here's why we're excited: 🧵👇🏾

New work 🎉: conformal classifiers return sets of classes for each example, with a probabilistic guarantee the true class is included. But these sets can be too large to be useful. In our #CVPR2025 paper, we propose a method to make them more compact without sacrificing

I wrote about science cuts and my family's immigration story as part of the McClintock Letters initiative. Haven't yet placed it in a Houston-based newspaper but hopefully it's useful here gargnikhil.com/posts/20250614…

I can’t believe I’m saying this: our work received a Best Paper Award at #CHIL2025!! So so excited and grateful 🥰 Looking forward to day 2 of the conference with these awesome people :)