甲骨文研究迎来AI新视角，多模态大模型能否读懂句子级古文字？这份评测给出答案。
arXiv:2606.31169v1 Announce Type: new Abstract: Existing AI-assisted oracle bone inscription (OBI) visual recognition and understanding studies mainly…
用AI光谱成像技术“卸妆”古油画，揭秘画作底层化学成分的混合算法研究。
arXiv:2603.06673v2 Announce Type: replace-cross Abstract: Spectroscopic imaging (SI) has become central to heritage science because it enables non-inv…
CVPR 2026录用论文，提出智能体驱动的古代铭文恢复系统，实现精准的破损文字重建。
arXiv:2604.09367v2 Announce Type: replace Abstract: Ancient inscriptions, as repositories of cultural memory, have suffered from centuries of environm…
视觉语言模型正被广泛应用于文化遗产领域，但一篇新研究揭示了其隐藏的硬伤：文化时代错位。模型难以准确理解历史文物中的时间语境，尤其在非西方视觉文化上表现糟糕。这项基准测试戳中了多模态AI无法跨越的文化盲区。
arXiv:2605.15071v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital …