<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Irene Y. Chen - UC Berkeley and UCSF</title><link>https://www.irenechen.net/</link><description>Recent content on Irene Y. Chen - UC Berkeley and UCSF</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 11 May 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://www.irenechen.net/index.xml" rel="self" type="application/rss+xml"/><item><title>De-Identified Quotes on AI and Medicine from SAIL 2025</title><link>https://www.irenechen.net/sail2025/</link><pubDate>Sun, 11 May 2025 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/sail2025/</guid><description>I spent the last week at SAIL 2025, an intimate conference in Puerto Rico of clinicians, patient advocates, academics, hospital executives, and many others. The sunsets were beautiful, and the conversations were candid. Because the conference operates under Chatham House Rule, I&amp;rsquo;ve compiled some de-identified quotes &amp;ndash; both from the stage and in smaller discussions &amp;ndash; that capture the complexities and contradictions of the current state of medical AI.
On clinical innovation:</description></item><item><title>My First 100 Days as a Professor</title><link>https://www.irenechen.net/first100/</link><pubDate>Thu, 23 May 2024 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/first100/</guid><description>NeurIPS submissions are done, grades are entered, and thus my second semester as professor has ended. In contrast to the academic job market which has many online guides, there are fewer resources for being a professor. Basically none focus on the transition to junior faculty. In an effort to fill that gap, here are my reflections and learnings from my first 100 days as an assistant professor.
Everything is an experiment.</description></item><item><title>Bio</title><link>https://www.irenechen.net/about-me/</link><pubDate>Sat, 06 May 2023 11:55:56 -0400</pubDate><guid>https://www.irenechen.net/about-me/</guid><description>Irene Chen is an assistant professor at UC Berkeley and UCSF. She studies machine learning systems for healthcare to be more robust, impactful, and equitable. Her work has been published in machine learning conferences (NeurIPS, AAAI) and medical journals (Nature Medicine, Lancet Digital Health), and has been covered by media outlets including MIT Tech Review, NPR/WGBH, and Stat News. She has been named a Rising Star in EECS, Machine Learning, and Data Science.</description></item><item><title>Post</title><link>https://www.irenechen.net/post/</link><pubDate>Sat, 06 May 2023 11:33:28 -0400</pubDate><guid>https://www.irenechen.net/post/</guid><description/></item><item><title>MLHC 2018 Recap</title><link>https://www.irenechen.net/mlhc2018/</link><pubDate>Tue, 28 Aug 2018 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/mlhc2018/</guid><description>Over 300 clinicians and machine learning researchers met in Palo Alto for three days of tutorials, keynotes, and papers.</description></item><item><title>30 Things I Learned at MLHC 2017</title><link>https://www.irenechen.net/mlhc2017/</link><pubDate>Tue, 22 Aug 2017 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/mlhc2017/</guid><description>Didn&amp;rsquo;t go? Went and forgot everything? Here&amp;rsquo;s your Machine Learning for Healthcare 2017 recap in 30 bullet points.</description></item><item><title>The Gumbel Trick</title><link>https://www.irenechen.net/gumbel/</link><pubDate>Thu, 17 Aug 2017 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/gumbel/</guid><description>Calculating log-partition functions for discrete probabiity distributions has never been so easy.</description></item><item><title/><link>https://www.irenechen.net/home/blurb/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/home/blurb/</guid><description>I work to build trustworthy and reliable AI. My research program spans clinical decision-making, fairness and inequality in machine learning, and rigorous evaluation of increasingly advanced AI systems.
I am an Assistant Professor at UC Berkeley and UCSF in CPH, EECS, and BAIR. My research has been recognized with best paper and best poster awards, honors from Google and Apple, and Rising Star awards in EECS, Machine Learning, and Data Science.</description></item><item><title/><link>https://www.irenechen.net/talks/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/talks/</guid><description> Research Talks MIT J-Clinic AI for Healthcare Equity Talk MIT J-Clinic AI for Healthcare Equity Teaser Harvard CRCS Rising Stars Talk Harvard DBMI Open Insights MIT News, "The Heart of the Matter" NeurIPS 2018 Interviews and Panels Visible Women Podcast with Caroline Criado Perez TWiML AI Podcast with Sam Charington UT-Austin Fairness in Machine Learning Panel AI Talk with Karen Hao Boston Local NPR with Heather Goldstone</description></item><item><title>Advising Statement</title><link>https://www.irenechen.net/advising-statement/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/advising-statement/</guid><description>One of my goals as an advisor for postdocs, PhD students, and undergraduate researchers in the lab is to train the next generation of researchers. Here I describe my expectations for a healthy and productive advisor-advisee relationship.
Student Development: The goal of the PhD is for students to develop their own research directions and the skill set necessary for independent work. Towards that goal, students are encouraged to explore a wide array of areas, to develop computational maturity through coursework or engagement with the scientific literature, and to refine their &amp;ldquo;research taste.</description></item><item><title>asdf</title><link>https://www.irenechen.net/home/papers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/home/papers/</guid><description>Selected Papers (Show all) Aggregated Individual Reporting for Post-Deployment Evaluation.
Jessica Dai, Inioluwa Deborah Raji, Benjamin Recht, and Irene Y. Chen. ICML 2026. Falsifying Sparse Autoencoder Reasoning Features in Language Models.
George Ma, Zhongyuan Liang, Irene Y. Chen, Somayeh Sojoudi. ICML 2026. Access to care improves EHR reliability and clinical risk prediction model performance.
Anna Zink, Hongzhou Luan, Irene Y Chen. Nature Health 2026. Patient Safety Risks from AI Scribes: Signals from End-User Feedback.</description></item><item><title>Awards</title><link>https://www.irenechen.net/sidebar/3-awards/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/sidebar/3-awards/</guid><description>Best Findings Paper, ML4H 2024
Best Poster, CERSI Scientific Symposium 2024
Google Research Scholar 2024
Apple Machine Learning Research Grant 2024
Rising Star in AI - Harvard CRCS 2021
Rising Star in EECS - University of California Berkeley 2021
Rising Star in ML - University of Maryland 2021
Neurips Top 400 Reviewer 2019
Seth J. Teller Award for Excellence, Inclusion, and Diversity 2018
PD Soros Fellowship Finalist 2018
Derek Bok Certificate of Distinction in Teaching 2011</description></item><item><title>Contact Info</title><link>https://www.irenechen.net/sidebar/1-contact/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/sidebar/1-contact/</guid><description>Email: iychen@berkeley.edu
Twitter: @irenetrampoline
Github: irenetrampoline
Google Scholar</description></item><item><title>Join the Lab</title><link>https://www.irenechen.net/work-with-me/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/work-with-me/</guid><description>We are actively recruiting research assistants/engineers, visiting students, and postdoctoral fellows. We are especially interested in hearing from individuals from nontraditional or underrepresented backgrounds. If you are interested in joining or learning more about the lab, please read position-level descriptions below and email Irene (iychen at berkeley dot edu).
Please include in your email:
Your CV A brief (1-3 sentence) description of your research background and experience The position you&amp;rsquo;re interested in (e.</description></item><item><title>Reading List</title><link>https://www.irenechen.net/reading-list/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/reading-list/</guid><description>I like to share what I&amp;rsquo;m reading to keep me motivated. Below are books I&amp;rsquo;ve read.
Books I&amp;rsquo;ve especially loved are marked with an asterik.
2026 On the Calculation of Volume I, Solvej Balle* On the Calculation of Volume II, Solvej Balle* On the Calculation of Volume III, Solvej Balle* Yesteryear, Caro Claire Burke Strangers, Belle Burden* The Wedding People, Alison Espach On the Calculation of Volume IV, Solvej Balle* There Is No Antimemetics Division, qntm* Julius Caesar, William Shakespeare* Antimemetics, Nadia Asparouhova As I Lay Dying, William Faulkner* Luster, Raven Leilani* Small Things Like These, Claire Keegan* Foster, Claire Keegan* 2025 The Anthropocene Reviewed, John Green* Make Something Wonderful, Steve Jobs* Welcome to the Monkey House, Kurt Vonnegut* all about love, bell hooks Dubliners, James Joyce* All Fours, Miranda July* Orbital, Samantha Harvey The Body Keeps the Score, Bessel Van Der Kolk* The Power Broker, Robert A.</description></item><item><title>Recent News</title><link>https://www.irenechen.net/sidebar/2-news/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/sidebar/2-news/</guid><description>Jul 2026: We investigate how uncertainty drives social bias change in new research accepted to COLM 2026. Congratulations Stan and Sanae!
Apr 2026: Two papers accepted to ICML 2026! See our work on leveraging public feedback for AI evals and debunking SAE reasoning features. Congrats Jessica and Zhongyuan!
Dec 2025: New papers! Two at ML4H on patient safety and one on AI scribe evaluation. Also two papers at AIES 2025 on legal investigations of algorithmic bias and privacy-preserving data combination.</description></item><item><title>Resources</title><link>https://www.irenechen.net/resources/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/resources/</guid><description>Advice for aspiring and current ML researchers Enormous list of resources for all things research-related &amp;ndash; by Shaily Bhatt (@shaily99) Applications for computer science PhD &amp;ndash; by Jean Yang (@jeanqasaur) Applying to Ph.D. Programs in Computer Science &amp;ndash; by Mor Harchol-Balter Emailing professors &amp;ndash; by Dan Roy (@roydanroy) Interviewing for PhD programs &amp;ndash; by Nils Gehlenborg (@ngehlenborg) What should grad students be learning? &amp;ndash; by Michael Mitzenmacher Starting out in AI research &amp;ndash; by Tom Silver (@tomssilver) Expectations for advisors and students &amp;ndash; by John Regehr (@johnregehr), Suresh Venkatasubramanian (@geomblog), and Matt Might (@mattmight) PhD Syllabus &amp;ndash; by Mor Naaman (@informor) Handling math bullies &amp;ndash; by Fan Chung Graham Combatting Anti-Blackness in the AI Community &amp;ndash; by Devin Guillory (@databoydg) Paper writing tips &amp;ndash; by Jacob Steinhardt Shortening papers &amp;ndash; by Devi Parikh (@deviparikh) Responding to peer feedback &amp;ndash; by Matt Might (@mattmight) Writing conference rebuttals &amp;ndash; by Devi Parikh (@deviparikh), Dhruv Batra (@DhruvBatraDB), Stefan Lee (@stefmlee) Tweeting about papers &amp;ndash; by Lisa Nivison-Smith (@LNivisonSmith) Reviewing conference papers &amp;ndash; by Colin Raffel (@colinraffel) How to write a good conference review &amp;ndash; CVPR 2020 Tutorial Academic job search in 10 questions &amp;ndash; by Elissa Redmiles (@eredmil1) and Nicolas Papernot (@NicolasPapernot) Another academic job search guide &amp;ndash; by Westley Weimer How to reject a candidate &amp;ndash; by Sara Davis (@PsySciSar) Where to present research on machine learning, healthcare, and/or fairness Neural Information Processing Systems (NeurIPS) International Conference for Machine Learning (ICML) ACM Conference on Health, Inference, and Learning (CHIL) Fair ML for Health Workshop at NeurIPS Machine Learning for Health (ML4H) Workshop at NeurIPS Representative Machine Learning Women in Machine Learning Black in AI Queer in AI LatinX in AI (Dis)Ability in AI Muslims in ML Introductory guides Causal Inference textbook &amp;ndash; by Miguel Hernan and Jamie Robins History of Fairness in ML &amp;ndash; by Ben Hutchinson and Margaret Mitchell ML for Healthcare class at MIT &amp;ndash; by course staff including myself</description></item><item><title>Service</title><link>https://www.irenechen.net/sidebar/4-organizing/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/sidebar/4-organizing/</guid><description>AI and Society Organizer 2025-
AHLI Board Member 2022-
CHIL 2025 General Chair
NeurIPS 2024 Tutorial Chair
CHIL 2024 Program Chair
NeurIPS 2023 Comms Chair
Toward Algorithmic Justice in Precision Medicine 2023 Advisory Committee
FAccT 2023 Doctoral Colloquium Chair
ML4H Symposium 2022 General Chair
CHIL Tutorials Chair 2020-21
CHIL 2020 Track Chair
Fair ML for Health Workshop at NeurIPS 2019 Founder and Co-Chair
ML4H Workshop at NeurIPS Organizer (2018-2020)</description></item><item><title>Working with the Chen Lab</title><link>https://www.irenechen.net/join-lab/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://www.irenechen.net/join-lab/</guid><description>Thank you for your interest in working with us! Please read my advising statement for more information about what it&amp;rsquo;s like working with our lab.
Prospective PhD students: The Chen Lab is looking for 1-2 PhD students starting Fall 2027. Apply through the Computational Precision Health or EECS (AI-H) admissions portals. If you are a US citizen or permanent resident, you may be eligible for a fee waiver. Unfortunately due to volume, we cannot respond to all emails about PhD admissions, but I do read every email I receive.</description></item></channel></rss>