Leo Schwinn's picture

3 4

Leo Schwinn

SchwinnL

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Diffusion LLMs are Natural Adversaries for any LLM

authored a paper about 1 month ago

Efficient Adversarial Training in LLMs with Continuous Attacks

authored a paper about 1 month ago

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

View all activity

Organizations

upvoted 2 papers about 1 month ago

Diffusion LLMs are Natural Adversaries for any LLM

Paper • 2511.00203 • Published Oct 31, 2025 • 1

A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Paper • 2603.06594 • Published Feb 4 • 1

upvoted a collection about 1 month ago

CoinflipForSafety

Datasets from the paper: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness (arxiv: https://arxiv.org/abs/2603.06594) • 4 items • Updated Mar 16 • 1