AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

StrucTab: A Structured Optimization Framework for Table Parsing

Gengluo Li, Shangpin Peng, Chengquan Zhang, Binghong Wu, Hao Feng, Weinong Wang, Pengyuan Lyu, Huawen Shen, Xingyu Wan, Zhuotao Tian, Han Hu, Can Ma and 1 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 5 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 row-column counting subtask (ablation)StrucTab baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 86.26 -> 87.43Improved
add merged-cell analysis subtask (ablation)StrucTab baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 86.26 -> 87.39Improved
combine row-column counting and merged-cell analysis (ablation)StrucTab baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 87.43 -> 88.93Improved
unify subtasks into sequential reasoning (ablation)independent subtasks (d) · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 88.93 -> 90.11Improved
add first-stage curriculum of independent subtasks before sequential reasoning (ablation)Seq reasoning · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 89.54 -> 90.11Improved
add Uni-TabRL to SFT modelStrucTab-SFT · Average TEDS across four benchmarksTEDS: 85.87 -> 88.79Improved
add GRPO RL with TEDS rewards (ablation)StrucTab-SFT · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 90.11 -> 91.29Improved
replace TEDS content reward with VLM consistency judge (ablation)RL baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 91.29 -> 90.51Hurt
replace TEDS content reward with Anchor-Guided Destylization (ablation)RL baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 91.29 -> 91.76Improved
replace TEDS-S structure reward with 1D Probe (ablation)RL baseline · Open-source benchmarks average (OmniDocBench, CC-OCR, OCRBench v2)TEDS: 91.29 -> 91.80Improved
combine Anchor-Guided Destylization and 1D Probe (ablation)RL baseline · TableVerse-5KTEDS: 86.45 -> 87.81Improved
use 1D Probe structure reward instead of TEDS-S (ablation)RL · TableVerse-5Krepetition rate: 1.20% -> 1.02%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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