SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
Paper
•
2506.08889
•
Published
•
24
LLM
-
-
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 90 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 256 -
OpenThoughts: Data Recipes for Reasoning Models
Paper • 2506.04178 • Published • 44 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 280 -
Phi-4-reasoning Technical Report
Paper • 2504.21318 • Published • 51 -
Efficient Inference for Large Reasoning Models: A Survey
Paper • 2503.23077 • Published • 47 -
The Diffusion Duality
Paper • 2506.10892 • Published • 38