OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Kenny Peng
PhD student, Computer Science, Cornell University
Joined
May 2021
Names
Kenny Peng
(Preferred)
,
Kenneth L Peng
Emails
****@princeton.edu
(Confirmed)
,
****@cornell.edu
(Confirmed)
Personal Links
Homepage
Career & Education History
PhD student
Computer Science,
Cornell University
(cornell.edu)
2022
–
Present
Undergrad student
Mathematics,
Princeton University
(princeton.edu)
2018
–
2022
Advisors, Relations & Conflicts
PhD Advisor
Nikhil Garg
Present
PhD Advisor
Jon Kleinberg
Present
Coauthor
Éva Tardos
Present
Coauthor
Emma Pierson
Present
Coauthor
Manish Raghavan
Present
Coauthor
Emily Ryu
Present
Coauthor
Arvind Narayanan
Present
Coauthor
Sayash Kapoor
Present
Coauthor
Rajiv Movva
Present
Coauthor
Gabriel Agostini
Present
Coauthor
Sidhika Balachandar
Present
Expertise
No areas of expertise listed
Publications
Position: Use Sparse Autoencoders to Discover Unknowns
Kenny Peng
,
Rajiv Movva
,
Jon Kleinberg
,
Emma Pierson
,
Nikhil Garg
Mech Interp Workshop ICML 2026 viafasttrackPoster
Readers:
Everyone
A Theory of Atomic Features and Four Testable Predictions
Kenny Peng
,
Jon Kleinberg
,
Nikhil Garg
CompLearn 2026 Poster
Readers:
Everyone
How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
Nikhil Garg
,
Jon Kleinberg
,
Kenny Peng
CompLearn 2026 Poster
Readers:
Everyone
Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts
Kenny Peng
,
Rajiv Movva
,
Jon Kleinberg
,
Emma Pierson
,
Nikhil Garg
Submitted to NeurIPS 2025 Position Paper Track
Readers:
Everyone
Correlated Errors in Large Language Models
Elliot Myunghoon Kim
,
Avi Garg
,
Kenny Peng
,
Nikhil Garg
ICML 2025 poster
Readers:
Everyone
Sparse Autoencoders for Hypothesis Generation
Rajiv Movva
,
Kenny Peng
,
Nikhil Garg
,
Jon Kleinberg
,
Emma Pierson
ICML 2025 poster
Readers:
Everyone
Monoculture in Matching Markets
Kenny Peng
,
Nikhil Garg
NeurIPS 2024 poster
Readers:
Everyone
Reconciling the accuracy-diversity trade-off in recommendations
Kenneth L Peng
,
Manish Raghavan
,
Emma Pierson
,
Jon Kleinberg
,
Nikhil Garg
TheWebConf24 Oral
Readers:
Everyone
Mitigating dataset harms requires stewardship: Lessons from 1000 papers
Kenneth L Peng
,
Arunesh Mathur
,
Arvind Narayanan
Published: 11 Oct 2021, Last Modified: 12 Oct 2025
NeurIPS 2021 Datasets and Benchmarks Track (Round 2)
Readers:
Everyone
Co-Authors
Arunesh Mathur
Arvind Narayanan
Avi Garg
Elliot Myunghoon Kim
Emma Pierson
Jon Kleinberg
Manish Raghavan
Nikhil Garg
Rajiv Movva