TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation Paper • 2503.04872 • Published 5 days ago • 11
Stress Testing Generalization: How Minor Modifications Undermine Large Language Model Performance Paper • 2502.12459 • Published 21 days ago
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation Paper • 2503.04872 • Published 5 days ago • 11
Expand VSR Benchmark for VLLM to Expertize in Spatial Rules Paper • 2412.18224 • Published Dec 24, 2024
LongAttn: Selecting Long-context Training Data via Token-level Attention Paper • 2502.16860 • Published 15 days ago
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision Paper • 2502.20790 • Published 11 days ago
Light-R1 Collection Surpassing R1-Distill from Scratch* with 70k Math Data through Curriculum SFT & DPO • 3 items • Updated 7 days ago • 9
Light-R1 Collection Surpassing R1-Distill from Scratch* with 70k Math Data through Curriculum SFT & DPO • 3 items • Updated 7 days ago • 9