Erica Chiang
@ericachiang.bsky.social
📤 86
📥 83
📝 14
CS PhD student at Cornell :) CMU CS ‘23
https://erica-chiang.github.io
pinned post!
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
loading . . .
9 months ago
3
36
17
reposted by
Erica Chiang
Divya Shanmugam
3 months ago
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.
1
21
11
selfishly i wish we could keep divya in our lab forever but i guess it would be a disservice to the rest of the world 😅 she’s been such a wonderful mentor to me—i’ve learned a lot from how thoughtful, creative, and knowledgeable she is about everything. she’s also super funny and amazing at baking 🤭
add a skeleton here at some point
3 months ago
1
6
1
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 :)
add a skeleton here at some point
7 months ago
1
17
3
reposted by
Erica Chiang
Nikhil Garg
7 months ago
I wrote about science cuts and my family's immigration story as part of The McClintock Letters organized by
@cornellasap.bsky.social
. Haven't yet placed it in a Houston-based newspaper but hopefully it's useful here
gargnikhil.com/posts/202506...
loading . . .
Science and immigration cuts · Nikhil Garg
https://gargnikhil.com/posts/20250614_science_immigration_cuts/
2
26
6
reposted by
Erica Chiang
Divya Shanmugam
7 months ago
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.
3
22
7
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
loading . . .
9 months ago
3
36
17
reposted by
Erica Chiang
Emma Pierson
9 months ago
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...
loading . . .
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’.
https://www.nature.com/articles/d41586-025-01218-5
1
40
14
check out the findings from our
#dogathon
😍🐶 !!
add a skeleton here at some point
10 months ago
0
7
0
reposted by
Erica Chiang
Gabriel Agostini
10 months ago
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
loading . . .
5
42
19
reposted by
Erica Chiang
hal
10 months ago
Excited to announce a new preprint from my lab (with
@rishi-jha.bsky.social
and Vitaly Shmatikov; my first as a first author!) about severe security vulnerabilities in LLM-based multi-agent systems: “Multi-Agent Systems Execute Arbitrary Malicious Code”
arxiv.org/abs/2503.12188
1/12
1
8
2
reposted by
Erica Chiang
Kenny Peng
10 months ago
(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
1
14
6
reposted by
Erica Chiang
Raj Movva
10 months ago
💡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/
loading . . .
1
40
16
reposted by
Erica Chiang
Sophie Greenwood
10 months ago
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...
add a skeleton here at some point
8
162
129
reposted by
Erica Chiang
Sophie Greenwood
about 1 year ago
I'm excited to use my first post here to introduce the first paper of my PhD, "User-item fairness tradeoffs in recommendations" (NeurIPS 2024)! This is joint work with Sudalakshmee Chiniah and my advisor
@nkgarg.bsky.social
Description/links below: 1/
1
13
3
you reached the end!!
feeds!
log in