@jwkirchenbauer | LinkedIn | Google Scholar | GitHub | [email protected]
PhD Student at University of Maryland, College Park
Advised by Professor Tom Goldstein.
Deep Learning &/in/for Language Modeling
Research
In Tom Goldstein’s lab at the University of Maryland, I spent the first part of my PhD working on techniques to discern whether the thing you’re currently reading or looking at was created by a human or generated by an AI system. With the release of ChatGPT in 2022, all of a sudden, that became a very practical challenge. More generally, my research has explored robustness, reliability, and safety in deep learning as well as understanding how training data impacts model behavior. I am predominantly motivated by a belief that attempting (and often failing) to teach machines to understand the world is a good way to learn more about what the real building blocks of general intelligence are along the way.
About
Before starting my PhD at UMD, I worked at the Software Engineering Institute at Carnegie Mellon University as a research engineer (FFRDC). I completed a BS and MS in Computer Science at Washington University in St. Louis in 2020 and received a diploma in Violin from Oberlin College and Conservatory of Music in 2017. When not doing research, I like being in the mountains and listening to Mahler
Papers
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
ArXiv 2023
Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein
[Paper]
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
ArXiv 2023
Neel Jain*, Khalid Saifullah*, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
On the Reliability of Watermarks for Large Language Models
ArXiv 2023
John Kirchenbauer*, Jonas Geiping*, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
NeurIPS 2023
Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein
A Watermark for Large Language Models
ICML 2023, Outstanding Paper Award
John Kirchenbauer*, Jonas Geiping*, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
NeurIPS 2023
Yuxin Wen*, Neel Jain*, John Kirchenbauer, Micah Goldblum, Jonas Geiping, Tom Goldstein
GOAT: A Global Transformer on Large-scale Graphs
ICML 2023
Kezhi Kong, Jiuhai Chen, John Kirchenbauer, Renkun Ni, C Bayan Bruss, Tom Goldstein
[Paper]
How to Do a Vocab Swap? A Study of Embedding Replacement for Pre-trained Transformers
ArXiv 2022
Neel Jain*, John Kirchenbauer*, Jonas Geiping, Tom Goldstein
[Paper]
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability
ICLR 2022 Workshop on ML Evaluation Standards
John Kirchenbauer, Jacob R Oaks & Eric Heim
A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs
NeurIPS 2021 Workshop DistShift Spotlight
Mucong Ding*, Kezhi Kong*, Jiuhai Chen*, John Kirchenbauer, Micah Goldblum, David Wipf, Furong Huang, Tom Goldstein