AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents

Abstract

We present AnandaSky, a vision–language model for line-level transcription of historical sinographic documents. The model combines a compact high-resolution visual encoder with global attention, 10px patches, uncompressed visual prefix and a Qwen3-0.6B autoregressive decoder. It is trained at scale on 4M annotated lines from documents produced in China and Korea between the 8th and 20th centuries. Across in-domain and held-out public benchmarks, AnandaSky achieves sub-1% CER on five of eight datasets, sets a new state of the art on MTHv2 with 0.92% CER, and shows strong transfer to unseen collections. For EvaHan 2026, full fine-tuning on the organizers’ data to match task-specific annotation conventions reduces CER relative to the official baseline by 5.2% on prints and 12.1% on manuscripts, despite using one-tenth as many parameters.

Resources

Details