NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
inference scaling
4 papers
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
DISC: Dynamic Decomposition Improves LLM Inference Scaling
MR. Video: MapReduce as an Effective Principle for Long Video Understanding
The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training