SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.18146 · 2024

A Refer-and-Ground Multimodal Large Language Model for Biomedicine

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.18146.json · badge: /api/ran/2406.18146.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
shawnhuang497/bird canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
result2json Ran
ran; our contract draft was wrong, not the code
shawnhuang497/bird/applications/gradio_autolable.py
code served (permissive licence) · get_code("2cd7e10fb66b495a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from PIL import Image

# Create a mock result dict with required structure
# The function expects:
# - result['image']: PIL Image with size attribute (width, height)
# - result['labels']: list of label strings
# - result['boxes']: list of tensors with coordinates [xmin, ymin, xmax, ymax]
# - result['seg_masks']: list of tensors with segmentation masks

# Create a small PIL image
img = Image.new('RGB', (640, 480), color='red')

# Create labels
labels = ['cat(confidence_0.95)', 'dog']

# Create bounding boxes as tensors
boxes = [
    torch.tensor([100.0, 150.0, 250.0, 300.0]),
    torch.tensor([350.0, 200.0, 500.0, 400.0])
]

# Create segmentation masks
# Each mask should have shape (1, height, width) based on how the function uses it
# seg_mask = result['seg_masks'][i].numpy()[0] suggests shape (1, H, W)
seg_masks = [
    torch.ones((1, 480, 640), dtype=torch.float32),
    torch.zeros((1, 480, 640), dtype=torch.float32)
]
# Make masks have some structure for contour detection
seg_masks[0][0, 150:300, 100:250] = 1.0
seg_masks[1][0, 200:400, 350:500] = 1.0

result = {
    'image': img,
    'labels': labels,
    'boxes': boxes,
    'seg_masks': seg_masks
}

filename = 'test_image.jpg'

ARGS = {
    'result': result,
    'filename': filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_mask Not yet run
unverified (harvested, no recorded run)
shawnhuang497/bird/applications/gradio_autolable.py
code served (permissive licence) · get_code("17bafa39d1e2efb8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

With the rapid development of multimodal large language models (MLLMs), especially their capabilities in visual chat through refer and ground functionalities, their significance is increasingly recognized. However, the biomedical field currently exhibits a substantial gap in this area, primarily due to the absence of a dedicated refer and ground dataset for biomedical images. To address this challenge, we devised the Med-GRIT-270k dataset. It comprises 270k question-and-answer pairs and spans eight distinct medical imaging modalities. Most importantly, it is the first dedicated to the biomedical domain and integrating refer and ground conversations. The key idea is to sample large-scale biomedical image-mask pairs from medical segmentation datasets and generate instruction datasets from text using chatGPT. Additionally, we introduce a Refer-and-Ground Multimodal Large Language Model for Biomedicine (BiRD) by using this dataset and multi-task instruction learning. Extensive experiments have corroborated the efficacy of the Med-GRIT-270k dataset and the multi-modal, fine-grained interactive capabilities of the BiRD model. This holds significant reference value for the exploration and development of intelligent biomedical assistants.

For agents

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

get_harvested_code_for_paper("2406.18146")
get_code_for_paper("2406.18146")
have("2406.18146")

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

curl https://syntology.ai/api/ran/2406.18146.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.18146.svg)](https://syntology.ai/paper/2406.18146)

Connect an agent — have() is free.