URSA: Understanding and Verifying Chain-of-thought Reasoning in Multimodal Mathematics Paper • 2501.04686 • Published 11 days ago • 49
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published Dec 18, 2024 • 124
Towards Best Practices for Open Datasets for LLM Training Paper • 2501.08365 • Published 5 days ago • 41