AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning

Jiahe Song, Chuang Wang, Bowen Jiang, Yinfan Wang, Hao Zheng, Xingjian Wei, Chengjin Liu, Rui Nie, Junyuan Gao, Jiaxing Sun, Yubin Wang, Lijun Wu and 4 more

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Concept-guided image captioning · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use BIVP (box+index visual prompt) instead of BROS coordinate output (ablation)RxnCaption-VL · RxnScribe-testSoft F1: 76.2 -> 86.2Improved
use BIVP instead of BROS (ablation)RxnCaption-VL · U-RxnDiagram-15k-testHybrid F1: 57.2 -> 59.8Improved
use BIVP instead of BROS (ablation)Gemini-2.5-Pro (zero-shot) · RxnScribe-testSoft F1: 24.3 -> 76.1Improved
replace YoDe with MolYOLO detector (ablation)RxnCaption-VL · RxnScribe-testHybrid F1: 53.3 -> 72.2Improved
replace MolDetect with MolYOLO detector (ablation)RxnCaption-VL · RxnScribe-testHybrid F1: 70.8 -> 72.2Improved
supply ground-truth boxes to BIVP detector (ablation)RxnCaption-VL · U-RxnDiagram-15k-testHybrid F1: 59.8 -> 63.8Improved
use BIVP instead of BROS (inference speed) (ablation)RxnCaption-VL · A100 speedseconds per image: 16.88 -> 9.65Improved
train RxnScribe on U-RxnDiagram-15k (ablation)RxnScribe · U-RxnDiagram-15k-testHybrid F1: 34.9 -> 47.4Improved
train RxnScribe on U-RxnDiagram-15k (ablation)RxnScribe · RxnScribe-testHybrid F1: 69.1 -> 70.7Improved
use large synthetic RxnIM data instead of real data (ablation)RxnIM · U-RxnDiagram-15k-testSoft F1: 45.9 -> 40.5Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy