CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sun, 05 Oct 2025 21:00:23 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"68e2dc67-1f12" expires: Mon, 29 Dec 2025 23:06:40 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 1EC1:21D6A4:9743D2:A9A043:69530728 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 22:56:40 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210081-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767049000.433577,VS0,VE205 vary: Accept-Encoding x-fastly-request-id: 437f539e84d57d3defc32ed4bfbbdbba7f2367cc content-length: 2970 About Me | Yuxin Wen

Yuxin Wen

Google Scholar Profile

GitHub Profile

LinkedIn Profile

Twitter

About Me

I am a Ph.D. candidate in Computer Science at the University of Maryland, College Park, advised by Prof. Tom Goldstein.

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

Selected Publications [Full List]

Quantifying Cross-Modality Memorization in Vision-Language Models
Yuxin Wen, Yangsibo Huang, Tom Goldstein, Ravi Kumar, Badih Ghazi, Chiyuan Zhang
NeurIPS 2025
paper

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini
NeurIPS 2024
paper | code

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

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

Experience

Summer 2025, Research Scientist Intern, Meta FAIR, advised by Dr. Chuan Guo
Spring 2025, Student Researcher, Google AI, advised by Dr. Chiyuan Zhang
Summer 2024, Research Intern, Apple, advised by Dr. Mahyar Najibi
Fall 2023, Student Researcher, Google DeepMind, advised by Dr. Nicholas Carlini
Summer 2023, Research Intern, Sony AI, advised by Dr. Lingjuan Lv

Services

Reviewer: ICML, NeurIPS, ICLR

Contacts

ywen [ at ] umd [dot] edu

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

Original Source | Taken Source