I found this article on HF and saved it to read.
-
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
Paper ā¢ 2605.02290 ā¢ Published ā¢ 37 -
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Paper ā¢ 2605.06139 ā¢ Published ā¢ 65 -
ZAYA1-8B Technical Report
Paper ā¢ 2605.05365 ā¢ Published ā¢ 4 -
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Paper ā¢ 2511.06221 ā¢ Published ā¢ 134