Kenny Peng
@kennypeng.bsky.social
CS PhD student at Cornell Tech. Interested in interactions between algorithms and society. Princeton math '22.
kennypeng.me
kennypeng.me
I had a lot of fun making this map of Manhattan’s grid (only the numbered streets and avenues). Learned that 4th avenue doesn’t exist, but then learned that it actually does exist but only for a few blocks.
For #30DayMapChallenge day 11, a minimal map from @kennypeng.bsky.social.
Kenny extracts minimal elements from a not-as-minimal-as-it-seems object: the Manhattan street grid. "I show how Manhattan’s numbered grid of streets and avenues is more complicated than you might realize," he says.
Kenny extracts minimal elements from a not-as-minimal-as-it-seems object: the Manhattan street grid. "I show how Manhattan’s numbered grid of streets and avenues is more complicated than you might realize," he says.
November 17, 2025 at 2:54 PM
I had a lot of fun making this map of Manhattan’s grid (only the numbered streets and avenues). Learned that 4th avenue doesn’t exist, but then learned that it actually does exist but only for a few blocks.
Reposted by Kenny Peng
New #NeurIPS2025 paper: how should we evaluate machine learning models without a large, labeled dataset? We introduce Semi-Supervised Model Evaluation (SSME), which uses labeled and unlabeled data to estimate performance! We find SSME is far more accurate than standard methods.
October 17, 2025 at 4:29 PM
New #NeurIPS2025 paper: how should we evaluate machine learning models without a large, labeled dataset? We introduce Semi-Supervised Model Evaluation (SSME), which uses labeled and unlabeled data to estimate performance! We find SSME is far more accurate than standard methods.
Being Divya's labmate (and fellow ferry commuter) has been a real pleasure, and I've learned a ton from both her research itself and her approach to research (and also from the other random things she knows about).
I am on the job market this year! My research advances methods for reliable machine learning from real-world data, with a focus on healthcare. Happy to chat if this is of interest to you or your department/team.
October 14, 2025 at 4:02 PM
Being Divya's labmate (and fellow ferry commuter) has been a real pleasure, and I've learned a ton from both her research itself and her approach to research (and also from the other random things she knows about).
"those already relatively advantaged are, empirically, more able to pay time costs and navigate administrative burdens imposed by the mechanisms."
This point by @nkgarg.bsky.social has greatly shaped my thinking about the role of computer science in public service settings.
This point by @nkgarg.bsky.social has greatly shaped my thinking about the role of computer science in public service settings.
New piece, out in the Sigecom Exchanges! It's my first solo-author piece, and the closest thing I've written to being my "manifesto." #econsky #ecsky
arxiv.org/abs/2507.03600
arxiv.org/abs/2507.03600
August 12, 2025 at 1:04 PM
"those already relatively advantaged are, empirically, more able to pay time costs and navigate administrative burdens imposed by the mechanisms."
This point by @nkgarg.bsky.social has greatly shaped my thinking about the role of computer science in public service settings.
This point by @nkgarg.bsky.social has greatly shaped my thinking about the role of computer science in public service settings.
How do we reconcile excitement about sparse autoencoders with negative results showing that they underperform simple baselines? Our new position paper makes a distinction: SAEs are very useful for tools for discovering *unknown* concepts, less good for acting on *known* concepts.
August 5, 2025 at 5:26 PM
How do we reconcile excitement about sparse autoencoders with negative results showing that they underperform simple baselines? Our new position paper makes a distinction: SAEs are very useful for tools for discovering *unknown* concepts, less good for acting on *known* concepts.
One paragraph pitch for why sparse autoencoders are cool (they learn *interpretable* text embeddings)
July 30, 2025 at 5:22 PM
One paragraph pitch for why sparse autoencoders are cool (they learn *interpretable* text embeddings)
We're presenting two papers Wednesday at #ICML2025, both at 11am.
Come chat about "Sparse Autoencoders for Hypothesis Generation" (west-421), and "Correlated Errors in LLMs" (east-1102)!
Short thread ⬇️
Come chat about "Sparse Autoencoders for Hypothesis Generation" (west-421), and "Correlated Errors in LLMs" (east-1102)!
Short thread ⬇️
July 16, 2025 at 5:09 AM
We're presenting two papers Wednesday at #ICML2025, both at 11am.
Come chat about "Sparse Autoencoders for Hypothesis Generation" (west-421), and "Correlated Errors in LLMs" (east-1102)!
Short thread ⬇️
Come chat about "Sparse Autoencoders for Hypothesis Generation" (west-421), and "Correlated Errors in LLMs" (east-1102)!
Short thread ⬇️
Are LLMs correlated when they make mistakes? In our new ICML paper, we answer this question using responses of >350 LLMs. We find substantial correlation. On one dataset, LLMs agree on the wrong answer ~2x more than they would at random. 🧵(1/7)
arxiv.org/abs/2506.07962
arxiv.org/abs/2506.07962
July 3, 2025 at 12:54 PM
Are LLMs correlated when they make mistakes? In our new ICML paper, we answer this question using responses of >350 LLMs. We find substantial correlation. On one dataset, LLMs agree on the wrong answer ~2x more than they would at random. 🧵(1/7)
arxiv.org/abs/2506.07962
arxiv.org/abs/2506.07962
Reposted by Kenny Peng
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 coverage.
In our #CVPR2025 paper, we propose a method to make them more compact without sacrificing coverage.
June 14, 2025 at 3:00 PM
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 coverage.
In our #CVPR2025 paper, we propose a method to make them more compact without sacrificing coverage.
Reposted by Kenny Peng
We'll present HypotheSAEs at ICML this summer! 🎉
Draft: arxiv.org/abs/2502.04382
We're continuing to cook up new updates for our Python package: github.com/rmovva/Hypot...
(Recently, "Matryoshka SAEs", which help extract coarse and granular concepts without as much hyperparameter fiddling.)
Draft: arxiv.org/abs/2502.04382
We're continuing to cook up new updates for our Python package: github.com/rmovva/Hypot...
(Recently, "Matryoshka SAEs", which help extract coarse and granular concepts without as much hyperparameter fiddling.)
May 5, 2025 at 9:27 PM
We'll present HypotheSAEs at ICML this summer! 🎉
Draft: arxiv.org/abs/2502.04382
We're continuing to cook up new updates for our Python package: github.com/rmovva/Hypot...
(Recently, "Matryoshka SAEs", which help extract coarse and granular concepts without as much hyperparameter fiddling.)
Draft: arxiv.org/abs/2502.04382
We're continuing to cook up new updates for our Python package: github.com/rmovva/Hypot...
(Recently, "Matryoshka SAEs", which help extract coarse and granular concepts without as much hyperparameter fiddling.)
Reposted by Kenny Peng
I’m really excited to share the first paper of my PhD, “Learning Disease Progression Models That Capture Health Disparities” (accepted at #CHIL2025)! ✨ 1/
📄: arxiv.org/abs/2412.16406
📄: arxiv.org/abs/2412.16406
May 1, 2025 at 12:57 PM
I’m really excited to share the first paper of my PhD, “Learning Disease Progression Models That Capture Health Disparities” (accepted at #CHIL2025)! ✨ 1/
📄: arxiv.org/abs/2412.16406
📄: arxiv.org/abs/2412.16406
Reposted by Kenny Peng
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.
www.nature.com/articles/d41...
My answer today in Nature.
We will not be cowed. We will keep using AI to build a fairer, healthier world.
www.nature.com/articles/d41...
My ‘woke DEI’ grant has been flagged for scrutiny. Where do I go from here?
My work in making artificial intelligence fair has been noticed by US officials intent on ending ‘class warfare propaganda’.
www.nature.com
April 25, 2025 at 5:19 PM
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.
www.nature.com/articles/d41...
My answer today in Nature.
We will not be cowed. We will keep using AI to build a fairer, healthier world.
www.nature.com/articles/d41...
Our lab had a #dogathon 🐕 yesterday where we analyzed NYC Open Data on dog licenses. We learned a lot of dog facts, which I’ll share in this thread 🧵
1) Geospatial trends: Cavalier King Charles Spaniels are common in Manhattan; the opposite is true for Yorkshire Terriers.
1) Geospatial trends: Cavalier King Charles Spaniels are common in Manhattan; the opposite is true for Yorkshire Terriers.
April 2, 2025 at 2:16 PM
Our lab had a #dogathon 🐕 yesterday where we analyzed NYC Open Data on dog licenses. We learned a lot of dog facts, which I’ll share in this thread 🧵
1) Geospatial trends: Cavalier King Charles Spaniels are common in Manhattan; the opposite is true for Yorkshire Terriers.
1) Geospatial trends: Cavalier King Charles Spaniels are common in Manhattan; the opposite is true for Yorkshire Terriers.
Reposted by Kenny Peng
Migration data lets us study responses to environmental disasters, social change patterns, policy impacts, etc. But public data is too coarse, obscuring these important phenomena!
We build MIGRATE: a dataset of yearly flows between 47 billion pairs of US Census Block Groups. 1/5
We build MIGRATE: a dataset of yearly flows between 47 billion pairs of US Census Block Groups. 1/5
March 28, 2025 at 3:25 PM
Migration data lets us study responses to environmental disasters, social change patterns, policy impacts, etc. But public data is too coarse, obscuring these important phenomena!
We build MIGRATE: a dataset of yearly flows between 47 billion pairs of US Census Block Groups. 1/5
We build MIGRATE: a dataset of yearly flows between 47 billion pairs of US Census Block Groups. 1/5
Reposted by Kenny Peng
💡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/
Our method, HypotheSAEs, produces interpretable text features that predict a target variable, e.g. features in news headlines that predict engagement. 🧵1/
March 18, 2025 at 3:17 PM
💡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/
Our method, HypotheSAEs, produces interpretable text features that predict a target variable, e.g. features in news headlines that predict engagement. 🧵1/
(1/n) 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?
arxiv.org/abs/2502.04382
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?
arxiv.org/abs/2502.04382
March 18, 2025 at 3:29 PM
(1/n) 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?
arxiv.org/abs/2502.04382
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?
arxiv.org/abs/2502.04382
Reposted by Kenny Peng
Please repost to get the word out! @nkgarg.bsky.social and I are excited to present a personalized feed for academics! It shows posts about papers from accounts you’re following bsky.app/profile/pape...
March 10, 2025 at 3:12 PM
Please repost to get the word out! @nkgarg.bsky.social and I are excited to present a personalized feed for academics! It shows posts about papers from accounts you’re following bsky.app/profile/pape...
In new work, we show a "No Free Lunch Theorem" for human-AI Collaboration (w/ @nkgarg.bsky.social and Jon Kleinberg).
(And if you're at #AAAI, I'm presenting at 11:15am today in the Humans and AI session. Poster 12:30-2:30.)
arxiv.org/abs/2411.15230
(And if you're at #AAAI, I'm presenting at 11:15am today in the Humans and AI session. Poster 12:30-2:30.)
arxiv.org/abs/2411.15230
February 27, 2025 at 2:30 PM
In new work, we show a "No Free Lunch Theorem" for human-AI Collaboration (w/ @nkgarg.bsky.social and Jon Kleinberg).
(And if you're at #AAAI, I'm presenting at 11:15am today in the Humans and AI session. Poster 12:30-2:30.)
arxiv.org/abs/2411.15230
(And if you're at #AAAI, I'm presenting at 11:15am today in the Humans and AI session. Poster 12:30-2:30.)
arxiv.org/abs/2411.15230
I'm at #NeurIPS, presenting work w/ @nkgarg.bsky.social where we study algorithmic monoculture using a matching markets model: If many firms or colleges all use the same algorithm to evaluate applicants, what happens?
Poster is in a few hours, come chat!
Wed 11am-2pm | West Ballroom A-D #5505
Poster is in a few hours, come chat!
Wed 11am-2pm | West Ballroom A-D #5505
December 11, 2024 at 4:16 PM
I'm at #NeurIPS, presenting work w/ @nkgarg.bsky.social where we study algorithmic monoculture using a matching markets model: If many firms or colleges all use the same algorithm to evaluate applicants, what happens?
Poster is in a few hours, come chat!
Wed 11am-2pm | West Ballroom A-D #5505
Poster is in a few hours, come chat!
Wed 11am-2pm | West Ballroom A-D #5505