1
Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization
用全局归一化稳定多模态大模型基于策略的蒸馏，提升推理性能与训练效率的创新方法。
arXiv:2606.09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm. By using a s…