Joshua Kazdan
Scholar

Joshua Kazdan

Google Scholar ID: 2qhIm78AAAAJ
PhD Candidate in Statistics, Stanford University
machine learningAIdiffusion models
Google Scholar↗
Citations & Impact
All-time
Citations
66
 
H-index
5
 
i10-index
2
 
Publications
20
 
Co-authors
10
list available
Contact
No contact links provided.
Publications
12 items
Quantifying the Effect of Test Set Contamination on Generative Evaluations
arXiv.org · 2026
Cited
0
Efficient Prediction of Pass@k Scaling in Large Language Models
2025
Cited
0
Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
2025
Cited
0
Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
2025
Cited
0
Turning Down the Heat: A Critical Analysis of Min-p Sampling in Language Models
2025
Cited
0
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
2025
Cited
0
Position: Model Collapse Does Not Mean What You Think
2025
Cited
0
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data
2025
Cited
0
Resume (English only)
Co-authors
10 total
Sanmi Koyejo
Sanmi Koyejo
Assistant Professor, Stanford University
Rylan Schaeffer
Rylan Schaeffer
Stanford University
David Donoho
David Donoho
Professor f Statistics, Stanford University
Co-author 4
Co-author 4
Rafael Mitkov Rafailov
Rafael Mitkov Rafailov
Graduate Student, Stanford University
Apratim Dey
Apratim Dey
Stanford University
Co-author 7
Co-author 7
Stefano Ermon
Stefano Ermon
Stanford University