Joshua Kazdan
4 papers · 2025–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
โ
The Questioner
Top co-authors
Research topics
Keywords
generative model
(2)
empirical risk minimization
(1)
gradient descent
(1)
kernel density estimation
(1)
data privacy
(1)
diffusion model
(1)
heavy-tailed distribution
(1)
synthetic data
(1)
model collapse
(1)
membership inference
(1)
classifier guidance
(1)
language model fine-tuning
(1)
power-law scaling
(1)
inference compute
(1)
trade-off
(1)
unlearning
(1)
complexity
(1)
utility
(1)
aggregate success trend
(1)
exponential failure rate
(1)
Papers
Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World
ICML 2025
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
ICLR 2025
How Do Large Language Monkeys Get Their Power (Laws)?
ICML 2025
The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
ICLR 2025