SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.06071 · ACL · 2024

GroundingGPT: Language Enhanced Multi-modal Grounding Model

Qi Qi, Dong Zhang, Tao Wang, Junting Pan, Qi Xu, Hang Song, Ran Zhou, Van Vu, Yiqing Cai, Zhaowei Li, Zefeng Li, Zhida Huang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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; 2 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 5 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/2401.06071.json · badge: /api/ran/2401.06071.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
lzw-lzw/groundinggpt canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
lzw-lzw/lego canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
FunctionStatusWhere it lives
disabled_train Ran
ran, violated the contract we drafted
lzw-lzw/groundinggpt/video_llama/models/blip2.py
code served (permissive licence) · get_code("4cb732f513d69dfd")
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) and returned SimpleModel. 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 torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "self": model,
    "mode": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
load_image_from_base64 Ran
ran, honoured the contract we drafted
lzw-lzw/groundinggpt/lego/mm_utils.py
code served (permissive licence) · get_code("c3ee9d07c900dd55")
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 PngImageFile. 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 base64
from PIL import Image
from io import BytesIO
import numpy as np

# Create a small valid image in memory
img_array = np.uint8(np.random.rand(10, 10, 3) * 255)
img = Image.fromarray(img_array, mode='RGB')

# Encode to base64
buffer = BytesIO()
img.save(buffer, format='PNG')
buffer.seek(0)
image_base64 = base64.b64encode(buffer.read()).decode('utf-8')

ARGS = {
    'image': image_base64
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 3 and dtype family int 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
load_image_square Ran
ran, honoured the contract we drafted
lzw-lzw/groundinggpt/lego/mm_utils.py
code served (permissive licence) · get_code("f04e8e006a8831c9")
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 Image. 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.

from PIL import Image
import tempfile
import os

# Create a minimal image processor mock with image_mean attribute
class MockImageProcessor:
    def __init__(self):
        self.image_mean = [0.5, 0.5, 0.5]  # Normalized mean values

# Create a temporary test image file
def create_test_image():
    # Create a small 4x3 RGB image
    img = Image.new('RGB', (4, 3), color=(100, 150, 200))
    temp_file = tempfile.NamedTemporaryFile(suffix='.png', delete=False)
    img.save(temp_file.name)
    temp_file.close()
    return temp_file.name

image_file = create_test_image()
image_processor = MockImageProcessor()
image_aspect_ratio = 'pad'

ARGS = {
    'image_file': image_file,
    'image_processor': image_processor,
    'image_aspect_ratio': image_aspect_ratio
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
postprocess_box Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lzw-lzw/groundinggpt/lego/mm_utils.py
code served (permissive licence) · get_code("b8030ce2d52399ba")
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 tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# The function takes a box (tuple of 4 coordinates) and two dimensions
# and returns a postprocessed box tuple after adjusting for aspect ratio differences

box = (10, 20, 100, 120)  # x1, y1, x2, y2
ori_w = 640  # original width
ori_h = 480  # original height

ARGS = {
    "box": box,
    "ori_w": ori_w,
    "ori_h": ori_h,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
tile Ran
ran; our contract draft was wrong, not the code
lzw-lzw/groundinggpt/video_llama/models/base_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from MengzhouLu/RetroMPA, is pointer only (licence: NONE) · get_code("cb33571427334815")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from MengzhouLu/RetroMPA, and GitHub detected no licence in that repository 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.

violates_moderation Ran
ran, violated the contract we drafted
lzw-lzw/groundinggpt/lego/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Mi3-Lab/doScenes-VLM-Planning, is pointer only (licence: AGPL-3.0) · get_code("f9939a84b9a65279")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Mi3-Lab/doScenes-VLM-Planning, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

all_gather_with_grad Not yet run
unverified (harvested, no recorded run)
lzw-lzw/groundinggpt/video_llama/models/base_model.py
code served (permissive licence) · get_code("0ec9fc2025c16f65")
How it ran

no invocation recorded.

pretty_print_semaphore Not yet run
unverified (harvested, no recorded run)
lzw-lzw/groundinggpt/lego/utils.py
code served (permissive licence) · get_code("37899f22fb191b37")
How it ran

no invocation recorded.

save_image_to_local Not yet run
unverified (harvested, no recorded run)
lzw-lzw/lego/lego/serve/gradio_web_server.py
code served (permissive licence) · get_code("e2e5c3a95a6aebb4")
How it ran

no invocation recorded.

save_sound_to_local Not yet run
unverified (harvested, no recorded run)
lzw-lzw/lego/lego/serve/gradio_web_server.py
code served (permissive licence) · get_code("e75fa36a185a618d")
How it ran

no invocation recorded.

save_video_to_local Not yet run
unverified (harvested, no recorded run)
lzw-lzw/lego/lego/serve/gradio_web_server.py
code served (permissive licence) · get_code("22930d58d32e2d08")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 10 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 6 the same month, 10 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
disabled_train 173 other papers
75 dated earlier, 4 the same month, 86 later, 8 same year, order not determinable · 5 only as an assembly brick
2012.09841 (2020-12)
Taming Transformers for High-Resolution Image Synthesis
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
and 170 more not named here
all_gather_with_grad 91 other papers
40 dated earlier, 3 the same month, 44 later, 4 same year, order not determinable · 2 only as an assembly brick
2206.02967 (2022-06)
Masked Unsupervised Self-training for Label-free Image Classification
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
2302.06605 (2023-02)
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
and 88 more not named here
load_image_from_base64 85 other papers
16 dated earlier, 5 the same month, 60 later, 4 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2308.10253 (2023-08)
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
2309.07120 (2023-09)
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
and 82 more not named here
tile 84 other papers
40 dated earlier, 3 the same month, 36 later, 5 same year, order not determinable
2206.07699 (2022-06)
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
2210.07795 (2022-10)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning
2210.08773 (2022-10)
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
and 81 more not named here
violates_moderation 56 other papers
15 dated earlier, 40 later, 1 same year, order not determinable
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.03279 (2023-08)
UniversalNER: TARGETED DISTILLATION FROM LARGE LANGUAGE MODELS FOR OPEN NAMED ENTITY RECOGNITION
2308.13437 (2023-08)
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
and 53 more not named here
pretty_print_semaphore 54 other papers
13 dated earlier, 40 later, 1 same year, order not determinable
2106.06909 (2021-06)
GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
2308.13437 (2023-08)
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
2309.07120 (2023-09)
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
and 51 more not named here
save_image_to_local 7 other papers
1 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2304.08485 (2023-04)
Visual Instruction Tuning
Jin_Chat-UniVi_Unified_Visual_Representation_Empowers_Large_Language_Models_with_Image_CVPR_2024_paper (2024 (year only))
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
2401.15947 (2024-01)
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
and 4 more not named here
save_video_to_local 7 other papers
1 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2304.08485 (2023-04)
Visual Instruction Tuning
Jin_Chat-UniVi_Unified_Visual_Representation_Empowers_Large_Language_Models_with_Image_CVPR_2024_paper (2024 (year only))
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
2401.15947 (2024-01)
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
and 4 more not named here
load_image_square 1 other paper
1 later
2410.11623 (2024-10)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI
postprocess_box 1 other paper
1 later
2410.11623 (2024-10)
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

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 large language models (MLLMs) have demonstrated remarkable performance across various tasks. However, these models often prioritize capturing global information and overlook the importance of perceiving local information. This limitation hinders their ability to effectively understand fine-grained details and handle grounding tasks that necessitate nuanced comprehension. Although some recent works have made strides in this, they have primarily focused on single-modality inputs. Therefore, we propose Grounding-GPT, an end-to-end language enhanced multimodal grounding model. It is designed to perform fine-grained grounding tasks for three modalities: image, video and audio. To enhance the model's performance, we adopt a coarse-to-fine training strategy, utilizing a threestage training approach to progressively enhance the model's semantic awareness and finegrained understanding capabilities. Additionally, we employ a diversified stage-specific dataset construction pipeline, developing a multi-modal, multi-granularity dataset tailored for training the model in different stages. Extensive experiments conducted on multiple multimodal benchmarks demonstrate that our model achieves impressive fine-grained understanding of multi-modal inputs on grounding tasks while maintaining or improving its global comprehension capabilities. Our code, model, and dataset are available at https://github. com/lzw-lzw/GroundingGPT.

For agents

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

get_harvested_code_for_paper("2401.06071")
get_code_for_paper("2401.06071")
have("2401.06071")

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

curl https://syntology.ai/api/ran/2401.06071.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.06071.svg)](https://syntology.ai/paper/2401.06071)

Connect an agent — have() is free.