Tag
This paper proposes Golden-GRPO Injection (GRIN), a mixed-policy reinforcement learning framework for continual knowledge injection in large language models, overcoming limitations of supervised fine-tuning. Experiments demonstrate superior performance on knowledge absorption benchmarks.
Proposes Near-Future Policy Optimization (NPO), a mixed-policy RL method that accelerates convergence by learning from a later checkpoint of the same training run, boosting Qwen3-VL-8B-Instruct performance from 57.88 to 62.84.