Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published Nov 9 • 131
Running on CPU Upgrade Featured 2.73k The Smol Training Playbook 📚 2.73k The secrets to building world-class LLMs
Running 73 Unlocking On-Policy Distillation for Any Model Family 📝 73 Apply on-policy distillation to any model family
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models Paper • 2505.00551 • Published May 1 • 36