Pinned Loading

1. sunblaze-ucb/Intuitor sunblaze-ucb/Intuitor Public

   Code for the paper: "Learning to Reason without External Rewards"

   Python 383 42

2. WatermarkAttacker WatermarkAttacker Public

   [NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI

   Jupyter Notebook 253 35

3. weak-to-strong weak-to-strong Public

   [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models

   Python 91 10

4. PRC-Watermark PRC-Watermark Public

   [ICLR 2025] An Undetectable Watermark for Generative Image Models

   Python 66 13

5. Unigram-Watermark Unigram-Watermark Public

   [ICLR 2024] Provable Robust Watermarking for AI-Generated Text

   Python 38 8

6. pf-decoding pf-decoding Public

   [ICLR 2025] Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs

   Python 19