SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
Paper
•
2506.08889
•
Published
•
23
LLM
-
-
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 93 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 263 -
OpenThoughts: Data Recipes for Reasoning Models
Paper • 2506.04178 • Published • 49 -
Qwen3 Technical Report
Paper • 2505.09388 • Published • 320 -
Phi-4-reasoning Technical Report
Paper • 2504.21318 • Published • 53 -
Efficient Inference for Large Reasoning Models: A Survey
Paper • 2503.23077 • Published • 46 -
The Diffusion Duality
Paper • 2506.10892 • Published • 37 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 194 -
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 660