首个系统评估大模型在多种格式下表格理解能力的基准TABVERSE，揭示模型在处理跨格式表格时的缺陷与改进空间。
arXiv:2606.09578v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table r…
首个真实世界多模态表格理解基准，挑战AI模型对表格视觉与语义的联合解析能力。
arXiv:2505.21771v2 Announce Type: replace-cross Abstract: Multimodal tables i.e. tabular layouts interleaved with charts, maps, icons, and color encod…
用TableGrid导航与渐进推理提示，高效解决表格问答难题，已被ICDAR 2026录用。
arXiv:2605.20254v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance o…