Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published 3 days ago • 52
Running on CPU Upgrade 2.09k 2.09k The Smol Training Playbook 📚 The secrets to building world-class LLMs
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning Paper • 2507.00432 • Published Jul 1 • 79
view article Article I trained a Language Model to schedule events with GRPO! By anakin87 • Apr 29 • 90