作者位次 #2/6ACL 2026Poster· Natural Language Processing
Draft, Verify, Restore: Self-Refining Historical Inscription Restoration with a Unified MLLM
Yuyi Zhang · Junle Liu · Peirong Zhang · Jianliang Liu · Zhenhua Yang · Lianwen Jin
摘要
Inscriptions are invaluable cultural heritage, yet centuries of degradation (e.g., fractures, erosion, oxidation) have rendered many partially illegible. Existing Historical Inscription Restoration (HIR) methods rely on task-separated pipelines with irreversible error accumulation and patch-based...