1
Reinforcing Consistency in Video MLLMs with Structured Rewards
视频多模态模型常“看走眼”？这项研究用结构化奖励强化推理一致性，为视频理解立新标尺。
arXiv:2604.01460v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding.…