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

@misc{liu2026taming,
  title = {Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training},
  author = {Yibei Liu and Jiajun Chen and Qianle Zhang and Tangyue Jin and Mengying Zhu and Meng Xi and Yangyang Wu},
  year = {2026},
  eprint = {2608.03660},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.03660},
}