SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03491 · ICML · 2026

Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance

Min Zhang, Yang Xiang, Xiaoqiang Zhou, Kehai Chen, Xuefeng Bai, Yingjie Zhu, Youcheng Pan

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 2 no recorded run), measured 2026-11-21; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.03491.json · badge: /api/ran/2602.03491.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AAAndy-Zhu/TableVLM canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
convert_latex_table_to_html Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/evaluation/MMTab_evaluation.py
pointer only (licence: NONE) · get_code("70f06321036addf4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_markdown_table_to_html Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/evaluation/MMTab_evaluation.py
pointer only (licence: NONE) · get_code("3da4f3933abc2205")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_table_to_html_str Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/evaluation/MMTab_evaluation.py
pointer only (licence: NONE) · get_code("9541167465825c69")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt_qwen3_vl Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/TableGLS/src/eval_mmtab_vllm_da_cot.py
pointer only (licence: NONE) · get_code("168d1267e17419af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt_qwen3_vl Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/TableGLS/src/eval_mmtab_vllm_tablegls_stage1.py
pointer only (licence: NONE) · get_code("5113c20c236bc79d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt_qwen3_vl Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/TableGLS/src/eval_mmtab_vllm_tablegls_stage2.py
pointer only (licence: NONE) · get_code("65d8a336f62b2eef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt_qwen3_vl Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/TableGLS/src/eval_mmtab_vllm_tablegls_stage3.py
pointer only (licence: NONE) · get_code("72e3446ef5a55dba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_model_type Ran
ran; our contract draft was wrong, not the code
AAAndy-Zhu/TableVLM/DiSCo/src/eval_mmtab_understanding.py
pointer only (licence: NONE) · get_code("9c99f8bbb2a6e95d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_one Not yet run
unverified (harvested, no recorded run)
AAAndy-Zhu/TableVLM/DiSCo/src/eval_mmtab_understanding.py
pointer only (licence: NONE) · get_code("49998a6882281cd5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_model_and_processor Not yet run
unverified (harvested, no recorded run)
AAAndy-Zhu/TableVLM/DiSCo/src/eval_mmtab_understanding.py
pointer only (licence: NONE) · get_code("70aaeec9ccb88e17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AAAndy-Zhu/TableVLM when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Reasoning over table images remains challenging for Large Vision-Language Models (LVLMs) due to complex layouts and tightly coupled structure-content information. Existing solutions often depend on expensive supervised training, reinforcement learning, or external tools, limiting efficiency and scalability. This work addresses a key question: how to adapt LVLMs to table reasoning with minimal annotation and no external tools? Specifically, we first introduce DISCO, a Disentangled Structure-Content alignment framework that explicitly separates structural abstraction from semantic grounding during multimodal alignment, efficiently adapting LVLMs to tables structures. Building on DISCO, we further present Table-GLS, a Global-to-Local Structureguided reasoning framework that performs table reasoning via structured exploration and evidencegrounded inference. Extensive experiments across diverse benchmarks demonstrate that our framework efficiently enhances LVLM's table understanding and reasoning capabilities, particularly generalizing to unseen table structures. Our data and code are available at https:// github.com/AAAndy-Zhu/TableVLM.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.03491")
get_code_for_paper("2602.03491")
have("2602.03491")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.03491.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.03491.svg)](https://syntology.ai/paper/2602.03491)

Connect an agent — have() is free.