Preprint
Aug 2026
TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents
TongGuOCR is proposed, a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents that outperforms representative traditional task-specific OCR models, general-purpose MLLMs, and OCR-oriented MLLMs.
Zhongheng Zhou, Yi Sun, Huiguo He et al.
· 0 citations