Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs
Paper
•
2503.16870
•
Published
•
5
Todo
-
-
Gemma 3 Technical Report
Paper • 2503.19786 • Published • 52 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 158 -
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
Paper • 2503.19855 • Published • 28 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 19 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 124 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 95 -
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 108