Pinned Loading

1. UCSC-VLAA/STAR-1 UCSC-VLAA/STAR-1 Public

   [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

   Python 38 1

2. UCSC-VLAA/vllm-safety-benchmark UCSC-VLAA/vllm-safety-benchmark Public

   [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"

   Python 90 5

3. UCSC-VLAA/CIK-Bench UCSC-VLAA/CIK-Bench Public

   [EMNLP 2026] Official repository for Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

   Shell 68 2

4. UCSC-VLAA/AttnGCG-attack UCSC-VLAA/AttnGCG-attack Public

   [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

   Python 27 7

5. stanford-crfm/helm stanford-crfm/helm Public

   Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…

   Python 2.9k 410

6. NAG NAG Public

   [ICML 2026] Official implementation of Target-Oriented Pretraining Data Selection via Neuron-Activated Graph

   Python 7 1