SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.02422 · 2026

Watch Wider and Think Deeper: Collaborative Cross-modal Chain-of-Thought for Complex Visual Reasoning

Chao Wu, Tao Shen, Didi Zhu, Wenting Lu, Donglin Zhu, Ayong Ye

arXiv · PDF

Code that ran

8 of 9 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, 2 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2601.02422.json · badge: /api/ran/2601.02422.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
deer-echo/CoCoT canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
analyze_spatial_relationships Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
deer-echo/CoCoT/generate_relation_cycle.py
pointer only (licence: NONE) · get_code("7b1bd5d176fbfb7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

calculate_iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
deer-echo/CoCoT/generate_bbox_one_agent_qwen.py
pointer only (licence: NONE) · get_code("ebab022916f6a45b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

crop_bbox_from_image Ran
ran; our contract draft was wrong, not the code
deer-echo/CoCoT/generate_relation_cycle.py
pointer only (licence: NONE) · get_code("fd9eaf66df08d303")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

download_from_huggingface Ran
ran, violated the contract we drafted
deer-echo/CoCoT/download_model.py
pointer only (licence: NONE) · get_code("4aed29c54d32eee9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

download_from_modelscope Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
deer-echo/CoCoT/download_model.py
pointer only (licence: NONE) · get_code("e36f35d255375c57")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

extract_question_keywords Ran
ran; our contract draft was wrong, not the code
deer-echo/CoCoT/generate_relation_cycle.py
pointer only (licence: NONE) · get_code("5d609b463df9b79c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

remove_duplicate_bboxes Ran
ran; our contract draft was wrong, not the code
deer-echo/CoCoT/generate_bbox_one_agent_qwen.py
pointer only (licence: NONE) · get_code("9e74600602a4c71d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

verify_model_files Ran
ran, violated the contract we drafted
deer-echo/CoCoT/download_model.py
pointer only (licence: NONE) · get_code("18f4aa3717045405")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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.

adaptive_image_size Not yet run
unverified (harvested, no recorded run)
deer-echo/CoCoT/generate_bbox_one_agent_qwen.py
pointer only (licence: NONE) · get_code("1e80eec7bdf88545")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, deer-echo/CoCoT 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Multi-modal reasoning requires the seamless integration of visual and linguistic cues, yet existing Chain-of-Thought methods suffer from two critical limitations in cross-modal scenarios: (1) over-reliance on single coarse-grained image regions, and (2) semantic fragmentation between successive reasoning steps. To address these issues, we propose the CoCoT (Collaborative Coross-modal Thought) framework, built upon two key innovations: a) Dynamic Multi-Region Grounding to adaptively detect the most relevant image regions based on the question, and b) Relation-Aware Reasoning to enable multi-region collaboration by iteratively aligning visual cues to form a coherent and logical chain of thought. Through this approach, we construct the CoCoT-70K dataset, comprising 74,691 high-quality samples with multi-region annotations and structured reasoning chains. Extensive experiments demonstrate that CoCoT significantly enhances complex visual reasoning, achieving an average accuracy improvement of 15.4% on LLaVA-1.5 and 4.0% on Qwen2-VL across six challenging benchmarks. The data and code are available at: https://github.com/deer-echo/CoCoT.

For agents

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

get_harvested_code_for_paper("2601.02422")
get_code_for_paper("2601.02422")
have("2601.02422")

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

curl https://syntology.ai/api/ran/2601.02422.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.02422.svg)](https://syntology.ai/paper/2601.02422)

Connect an agent — have() is free.