Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation Paper • 2603.19220 • Published 16 days ago • 65
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning Paper • 2507.08267 • Published Jul 11, 2025 • 11
Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search Paper • 2503.04412 • Published Mar 6, 2025 • 5
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning Paper • 2507.08267 • Published Jul 11, 2025 • 11
Fast-Math Collection Fast-Math is a model series designed to significantly improve inference efficiency while preserving accuracy on math reasoning tasks. • 7 items • Updated Jul 15, 2025