AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Table-MCR2TR: Merged-Cell-Aware Table Recognition via Reinforced Multimodal Language Models

Bangbang Zhou, Zhaoqing Zhu, Feiyu Gao, Hangdi Xing, Yadong Qu, Qi Zheng, Ming Yan, Hongtao Xie

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 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
add MCT-350K data with TR-only SFT to base model (ablation)Qwen2.5-VL-3B · CC-OCR Scan+Photo averageTEDS: 76.7 -> 83.5Improved
add MCT-350K data with TR-only SFT to base model (ablation)Qwen2.5-VL-3B · CC-OCR Scan+Photo averageMCR F1: 46.4 -> 64.0Improved
add MCATR (3-task SFT plus M-CRL) on top of MCT-350K TR-only SFT (ablation)Qwen2.5-VL-3B · CC-OCR Scan+Photo averageMCR F1: 64.0 -> 73.9Improved
add MCATR on top of MCT-350K TR-only SFT (ablation)Qwen2.5-VL-3B · CC-OCR Scan+Photo averageTEDS: 83.5 -> 86.8Improved
add MCR F1 reward to alignment reward (ablation)M-CRL · CC-OCR Scan+Photo averageMCR F1: 70.7 -> 73.9Improved
add TEDS reward to alignment and F1 rewards (ablation)M-CRL · CC-OCR Scan+Photo averageTEDS: 85.7 -> 86.8Improved
add alignment reward to TEDS and F1 rewards (ablation)M-CRL · CC-OCR Scan+Photo averageMCR F1: 73.2 -> 73.9Improved
add RL (M-CRL) after 3-task joint SFT (ablation)Qwen2.5-VL-3B · CC-OCR Scan+Photo averageMCR F1: 67.9 -> 73.9Improved
use ground-truth merged-cell info instead of predicted MCR as input (ablation)Table-MCR2TR · CC-OCR ScanTEDS: 90.5 -> 93.9 (+3.4)Improved
use ground-truth merged-cell info instead of predicted MCR as input (ablation)Table-MCR2TR · CC-OCR PhotoTEDS: 83.0 -> 87.6 (+4.6)Improved
use ground-truth merged-cell info instead of predicted MCR as input (ablation)Table-MCR2TR · OmniDocBench tablesTEDS: 91.0 -> 93.6 (+2.6)Improved
add M-CRL after 3-task SFT on a 1B model (ablation)InternVL3-1B · CC-OCR Scan+Photo averageTEDS: 74.7 -> 80.2Improved

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