SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.09158 · 2023

General Object Foundation Model for Images and Videos at Scale

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 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/2312.09158.json · badge: /api/ran/2312.09158.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
FoundationVision/GLEE canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
agg_lang_feat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/GLEE/projects/GLEE/glee/models/glee_model.py
pointer only (licence: MIT); the stored copy get_code serves, from ProvenceStar/PartGLEE, is pointer only (licence: NONE) · get_code("95771c1a2d8346b7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ProvenceStar/PartGLEE, 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.

aligned_bilinear Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/vos_utils.py
code served (permissive licence) · get_code("29dbbaafa4be18e1")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 8, 10) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create a 4D tensor with shape (batch, channels, height, width)
# Using distinct sizes: batch=2, channels=3, height=4, width=5
tensor = torch.randn(2, 3, 4, 5)

# Factor must be >= 1 and an integer
factor = 2

ARGS = {
    "tensor": tensor,
    "factor": factor,
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 8, 10) — shape (2, 3, 8, 10) as a later run recorded it
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
batch_dice_loss Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/matcher.py
code served (permissive licence) · get_code("bc2cb481a75c370d")
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 Tensor, ndim 2, dtype family float, shape (2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Create small tensors for inputs and targets
# inputs: arbitrary shape float tensor (predictions)
# targets: same shape as inputs, binary classification labels (0 or 1)
# Using shape (2, 4) - batch size 2, 4 features
inputs = torch.randn(2, 4, dtype=torch.float32)
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

ARGS = {
    'inputs': inputs,
    'targets': targets,
}
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 Tensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) as a later run recorded it
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
dice_loss Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/criterion.py
code served (permissive licence) · get_code("89f75e54ff128be0")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Create small tensors for inputs and targets
# inputs should be arbitrary shape that can be flattened
inputs = torch.randn(2, 4, requires_grad=False)  # batch_size=2, features=4
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)  # same shape as inputs, binary labels

# num_masks is a float representing the number of masks for normalization
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
generate_regular_grid_point_coords Ran
ran, honoured the contract we drafted
FoundationVision/GLEE/projects/GLEE/glee/modules/point_features.py
code served (permissive licence) · get_code("42ab1750d0229462")
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 Tensor, ndim 3, dtype family float, shape (3, 16, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
from torch.nn import functional as F

torch.manual_seed(0)

ARGS = {
    "R": 3,
    "side_size": 4,
    "device": torch.device("cpu"),
}
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 Tensor, ndim 3, dtype family float, shape (3, 16, 2) — shape (3, 16, 2) as a later run recorded it
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
load_opt_from_config_files Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/train_net.py
pointer only (licence: MIT); the stored copy get_code serves, from ProvenceStar/PartGLEE, is pointer only (licence: NONE) · get_code("670bf62deb1d06af")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ProvenceStar/PartGLEE, 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.

masks_to_boxes Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/vos_utils.py
code served (permissive licence) · get_code("3e759ab7f3a7de8d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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)

# Create a simple mask tensor with shape [N, H, W]
# N=2 masks, H=4, W=3
masks = torch.randint(0, 2, (2, 4, 3), dtype=torch.float32)

ARGS = {
    "masks": masks
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
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
point_sample Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/modules/point_features.py
code served (permissive licence) · get_code("39e4af93b70bcddf")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# input: (N, C, H, W) - batch_size=2, channels=4, height=8, width=6
input_tensor = torch.randn(2, 4, 8, 6)

# point_coords: (N, P, 2) - batch_size=2, num_points=3, coordinates=2
# Values in [0, 1] range as required by the function
point_coords = torch.rand(2, 3, 2)

ARGS = {
    "input": input_tensor,
    "point_coords": point_coords,
}
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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
rand_sample Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FoundationVision/GLEE/projects/GLEE/glee/models/glee_model.py
pointer only (licence: MIT); the stored copy get_code serves, from ProvenceStar/PartGLEE, is pointer only (licence: NONE) · get_code("130323eef819c472")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ProvenceStar/PartGLEE, 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.

sigmoid_ce_loss Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/criterion.py
code served (permissive licence) · get_code("d0c61e8dba511aa3")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs: predictions (logits), arbitrary shape
# targets: binary labels (0 or 1), same shape as inputs
batch_size = 2
num_elements = 4

inputs = torch.randn(batch_size, num_elements, dtype=torch.float32)
targets = torch.randint(0, 2, (batch_size, num_elements), dtype=torch.float32)

# num_masks: used as divisor in the loss computation
num_masks = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_masks": num_masks,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
sigmoid_focal_loss Ran
ran; our contract draft was wrong, not the code
FoundationVision/GLEE/projects/GLEE/glee/models/criterion.py
code served (permissive licence) · get_code("5c0711aada67957e")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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.functional as F

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs: predictions (logits) - shape (2, 4) for batch_size=2, num_predictions=4
inputs = torch.randn(2, 4, requires_grad=True)

# targets: binary labels - shape (2, 4) matching inputs
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

# num_boxes: number of boxes for normalization
num_boxes = 2

# alpha and gamma are already float parameters with defaults
alpha = 0.25
gamma = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "num_boxes": num_boxes,
    "alpha": alpha,
    "gamma": gamma,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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
batch_sigmoid_ce_loss Not yet run
unverified (harvested, no recorded run)
FoundationVision/GLEE/projects/GLEE/glee/models/matcher.py
code served (permissive licence) · get_code("1edd24985036b0bf")
How it ran

no invocation recorded.

multi_head_attention_forward Not yet run
unverified (harvested, no recorded run)
FoundationVision/GLEE/projects/GLEE/glee/modules/attention.py
code served (permissive licence) · get_code("22a94fc69aed9aca")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 12 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 5 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
sigmoid_focal_loss 56 other papers
35 dated earlier, 18 later, 3 same year, order not determinable · 1 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 53 more not named here
dice_loss 46 other papers
23 dated earlier, 3 the same month, 17 later, 3 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 43 more not named here
sigmoid_ce_loss 45 other papers
22 dated earlier, 3 the same month, 17 later, 3 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 42 more not named here
batch_dice_loss 44 other papers
20 dated earlier, 3 the same month, 18 later, 3 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
batch_sigmoid_ce_loss 44 other papers
20 dated earlier, 3 the same month, 18 later, 3 same year, order not determinable
2112.01527 (2021-12)
Masked-attention Mask Transformer for Universal Image Segmentation
2112.10764 (2021-12)
Mask2Former for Video Instance Segmentation
2203.03605 (2022-03)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
and 41 more not named here
aligned_bilinear 17 other papers
11 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable · 1 only as an assembly brick
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2206.03789 (2022-06)
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
and 14 more not named here
point_sample 6 other papers
3 dated earlier, 3 later
2103.06564 (2021-03)
PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
2306.09347 (2023-06)
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
2311.14671 (2023-11)
SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation
and 3 more not named here
load_opt_from_config_files 3 other papers
1 dated earlier, 2 later
2305.10355 (2023-05)
Evaluating Object Hallucination in Large Vision-Language Models
2407.16696 (2024-07)
PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects
2025.emnlp-main.534 (2025 (year only))
On the Role of Model Prior in Real-World Inductive Reasoning
agg_lang_feat 1 other paper
1 later
2407.16696 (2024-07)
PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects
generate_regular_grid_point_coords 1 other paper
1 dated earlier
2306.09347 (2023-06)
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
multi_head_attention_forward 1 other paper
1 dated earlier
2306.09347 (2023-06)
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
rand_sample 1 other paper
1 later
2407.16696 (2024-07)
PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects

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

We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos. Through a unified framework, GLEE accomplishes detection, segmentation, tracking, grounding, and identification of arbitrary objects in the open world scenario for various object perception tasks. Adopting a cohesive learning strategy, GLEE acquires knowledge from diverse data sources with varying supervision levels to formulate general object representations, excelling in zero-shot transfer to new data and tasks. Specifically, we employ an image encoder, text encoder, and visual prompter to handle multi-modal inputs, enabling to simultaneously solve various object-centric downstream tasks while maintaining state-of-the-art performance. Demonstrated through extensive training on over five million images from diverse benchmarks, GLEE exhibits remarkable versatility and improved generalization performance, efficiently tackling downstream tasks without the need for task-specific adaptation. By integrating large volumes of automatically labeled data, we further enhance its zero-shot generalization capabilities. Additionally, GLEE is capable of being integrated into Large Language Models, serving as a foundational model to provide universal object-level information for multi-modal tasks. We hope that the versatility and universality of our method will mark a significant step in the development of efficient visual foundation models for AGI systems. The model and code will be released at https://glee-vision.github.io .

For agents

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

get_harvested_code_for_paper("2312.09158")
get_code_for_paper("2312.09158")
have("2312.09158")

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

curl https://syntology.ai/api/ran/2312.09158.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.09158.svg)](https://syntology.ai/paper/2312.09158)

Connect an agent — have() is free.