MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition Paper • 2308.09922 • Published Aug 19, 2023
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark Paper • 2412.15194 • Published 14 days ago • 1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer Paper • 2304.12043 • Published Apr 24, 2023 • 1
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning Paper • 2412.15797 • Published 13 days ago • 14