ICML 2026｜中国科学院大学×港中文×北京大学提出MIND推理框架：推动多模态推理从浅层模仿迈向深层认知

TL;DR - MIND is a general training framework that teaches multimodal language models to distinguish and correct faulty reasoning by learning from diverse positive and challenging negative rationales. It improves reasoning accuracy and robustness beyond conventional single-chain supervision.

• RAD automatically constructs varied correct rationales and semantically inverted hard negatives.
• Two-stage P2CL training first learns shared logic across correct rationales, then practices identifying and correcting errors.
• MCA contrastive alignment clusters correct rationales while separating misleading ones in embedding space.
• MIND improved results on ScienceQA, A-OKVQA, and M3CoT and transferred to Qwen2.5-VL, Qwen3-VL, and Qwen3.5 models.