RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning Paper • 2511.02384 • Published Nov 4, 2025 • 3
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing Paper • 2509.22186 • Published Sep 26, 2025 • 154
GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognition Paper • 2506.07553 • Published Jun 9, 2025 • 15