影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
64.73/100
前 3.6%
全站排名 #2,333
发表论文12 篇
平均评分
年均产出6.0 篇/年
Joshua Kazdan
研究方向
language models · diffusion models · generative models · deep networks · statistics · hypothesis testing · conformal prediction
15
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
ICLR 2026Poster
一作18
Efficient Prediction of pass@$k$ Scaling\\in Large Language Models
ICLR 2026Rejected
一作16
A $Min-p$ Blueprint for More Rigorous Science in Empirical Machine Learning Research
ICLR 2026Rejected
二作13
Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed
ICLR 2026Rejected
三作10
How Do Large Language Monkeys Get Their Power (Laws)?
ICML 2025Oral
二作20
KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
NeurIPS 2025Poster
三作24
The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
ICLR 2025Poster
二作23
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
NeurIPS 2025Rejected
一作31
Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World
ICLR 2025Rejected
一作18
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
COLM 2025Poster
二作15
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
ICLR 2025Poster
一作11
Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World
ICML 2025Poster
一作