👨💻
More
Pinned Loading
-
sail-sg/regmix
sail-sg/regmix Public[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)
-
sail-sg/D-TRAK
sail-sg/D-TRAK PublicIntriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
-
memorization
memorization PublicAn Empirical Study of Memorization in NLP (ACL 2022)
Jupyter Notebook 13
-
sail-sg/Cheating-LLM-Benchmarks
sail-sg/Cheating-LLM-Benchmarks Public[ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)
-
sail-sg/I-FSJ
sail-sg/I-FSJ PublicImproved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
-
sail-sg/Agent-Smith
sail-sg/Agent-Smith Public[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
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.