Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Paper • 2512.07525 • Published 18 days ago • 55
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning Paper • 2512.07461 • Published 18 days ago • 74
Running on CPU Upgrade Featured 2.69k The Smol Training Playbook 📚 2.69k The secrets to building world-class LLMs
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Paper • 2507.03336 • Published Jul 4 • 6
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Paper • 2507.03336 • Published Jul 4 • 6
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Paper • 2507.03336 • Published Jul 4 • 6 • 1