Pinned Loading

1. ATLAS ATLAS Public

   A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

   Python 963 98

2. SRe2L SRe2L Public

   (NeurIPS 2023 spotlight) Large-scale Dataset Distillation/Condensation, 50 IPC (Images Per Class) achieves the highest 60.8% on original ImageNet-1K val set.

   Python 129 20

3. Open-LLM-Leaderboard Open-LLM-Leaderboard Public

   Open-LLM-Leaderboard: Open-Style Question Evaluation. Paper at https://arxiv.org/abs/2406.07545

   Python 45 4

4. M-Attack M-Attack Public

   A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1. Paper at: https://arxiv.org/abs/2503.10635

   Python 63 2