Yuxin Wen


Google Scholar Profile

GitHub Profile

LinkedIn Profile


About Me

I am a third-year Computer Science Ph.D. student at the University of Maryland, College Park, advised by Prof. Tom Goldstein.

I am interested in computer vision and machine learning. My current research mainly focuses on security and privacy in generative models, including diffusion models and large language models.

Selected Publications [Full List]

Detecting, Explaining, and Mitigating Memorization in Diffusion Models
Yuxin Wen, Yuchen Liu, Chen Chen, Lingjuan Lyu
ICLR 2024 (Oral)
paper | code

NEFTune: Noisy Embeddings Improve Instruction Finetuning
Neel Jain*, Ping-yeh Chiang*, Yuxin Wen*, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
ICLR 2024
paper | code | tweet

Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein
NeurIPS 2023
paper | code | tweet | Yannic’s video

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Yuxin Wen*, Neel Jain*, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein
NeurIPS 2023
paper | code | demo | tweet

A Watermark for Large Language Models
John Kirchenbauer*, Jonas Geiping*, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein
ICML 2023 (Outstanding Paper Award)
paper | code | demo | tweet | The New York Times

Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein
ICLR 2023 (Spotlight)
paper | code

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
Yuxin Wen*, Jonas Geiping*, Liam Fowl*, Micah Goldblum, Tom Goldstein
ICML 2022
paper | code



Reviewer: ICML, NeurIPS, ICLR


ywen [ at ] umd [dot] edu

Iribe Center, Office 2116
8125 Paint Branch Dr,
College Park, MD 20742

Web Site Hit Counters