Training-inference mismatch in separated rollout and optimization stages of LLM RL can independently cause training collapse.
and Ermon, Stefano and Rudra, Atri and R\'
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Diagnosing Training Inference Mismatch in LLM Reinforcement Learning
Training-inference mismatch in separated rollout and optimization stages of LLM RL can independently cause training collapse.
- Real-Time Neural Hair Denoising