Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training

Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models. Under pronounced task distributional shifts, however, forgetting across representative RFT algorithms escalates sharply. This stems from the...