😎
study
Postdoc@UC Berkeley CS
-
UC Berkeley
- Berkeley
-
17:07
(UTC -12:00) - https://xuandongzhao.github.io/
- @xuandongzhao
- in/xuandong-zhao-a3270610b
Highlights
- Pro
Pinned Loading
-
WatermarkAttacker
WatermarkAttacker Public[NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI
-
-
Unigram-Watermark
Unigram-Watermark Public[ICLR 2024] Provable Robust Watermarking for AI-Generated Text
-
weak-to-strong
weak-to-strong PublicWeak-to-Strong Jailbreaking on Large Language Models
-
pf-decoding
pf-decoding PublicPermute-and-Flip: An optimally robust and watermarkable decoder for LLMs
Python 9
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.