😎
study
Postdoc@UC Berkeley CS
-
UC Berkeley
- Berkeley
-
22:30
(UTC -07:00) - https://xuandongzhao.github.io/
- @xuandongzhao
- in/xuandong-zhao-a3270610b
Highlights
- Pro
Pinned Loading
-
sunblaze-ucb/Intuitor
sunblaze-ucb/Intuitor PublicCode for the paper: "Learning to Reason without External Rewards"
-
WatermarkAttacker
WatermarkAttacker Public[NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI
-
weak-to-strong
weak-to-strong Public[ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
-
PRC-Watermark
PRC-Watermark Public[ICLR 2025] An Undetectable Watermark for Generative Image Models
-
Unigram-Watermark
Unigram-Watermark Public[ICLR 2024] Provable Robust Watermarking for AI-Generated Text
-
pf-decoding
pf-decoding Public[ICLR 2025] Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs
Python 19
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.