无监督域对齐新方法，跨模态迁移助力医学影像分析。
arXiv:2607.21546v1 Announce Type: new Abstract: Multimodal based approaches often outperform single modality approaches in downstream tasks as the dif…
大型推理模型在跨域隐喻理解上存在对齐偏差，揭示隐喻是模型跨域误对齐的关键来源，为提升AI语义鲁棒性提供新视角。
arXiv:2601.03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the quest…
神经符号架构让企业智能体摆脱LLM幻觉与领域漂移，实现合规推理
arXiv:2604.00555v4 Announce Type: replace-cross Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain …