SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09455 · 2022

To update or not to update? Neurons at equilibrium in deep models

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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, 1 violated it and 10 have no contract verdict; 3 failures 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/2207.09455.json · badge: /api/ran/2207.09455.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
eidoslab/neq canonical (classifier label)
classifier basis not recorded on the link
15 ran · 1 no recorded run
FunctionStatusWhere it lives
auto_resume_helper Ran
ran; our contract draft was wrong, not the code
eidoslab/neq/src/Swin-Transformer/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("0c32459bef92ff8c")
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 leaplabthu/inline, 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.

build_scheduler Ran
ran; our contract draft was wrong, not the code
eidoslab/neq/src/Swin-Transformer/lr_scheduler.py
pointer only (licence: MIT); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("c02cc4e0b5720211")
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 ghrua/seqpe, 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.

check_keywords_in_name Ran
ran, violated the contract we drafted
eidoslab/neq/src/Swin-Transformer/optimizer.py
pointer only (licence: MIT); the stored copy get_code serves, from leaplabthu/inline, is pointer only (licence: NONE) · get_code("b0a5beb34716d5a6")
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 leaplabthu/inline, 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.

cosine_similarity Ran
ran on a synthesized input
eidoslab/neq/src/general_utils.py
code served (permissive licence) · get_code("54151c79e61c0fd2")
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 1, dtype family float, shape (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 two small tensors for x1 and x2
# Using distinct shapes: x1 is (2, 4), x2 is (2, 4)
x1 = torch.randn(2, 4)
x2 = torch.randn(2, 4)

# dim parameter - compute cosine similarity along dimension 1
dim = 1

# eps parameter - small epsilon value for numerical stability
eps = 1e-08

ARGS = {
    "x1": x1,
    "x2": x2,
    "dim": dim,
    "eps": eps,
}
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 1, dtype family float, shape (2,) — shape (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
cosine_similarity Ran
ran on a synthesized input
eidoslab/neq/src/Swin-Transformer/general_utils.py
code served (permissive licence) · get_code("33df5cac0e385286")
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 1, dtype family float, shape (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)

# Construct tiny tensors for x1 and x2
# Using distinct shapes: batch_size=2, feature_dim=4
x1 = torch.randn(2, 4)
x2 = torch.randn(2, 4)

# dim parameter - reduce along feature dimension
dim = 1

# eps parameter - small value for numerical stability
eps = 1e-08

ARGS = {
    "x1": x1,
    "x2": x2,
    "dim": dim,
    "eps": eps,
}
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 1, dtype family float, shape (2,) — shape (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
create_logger Ran
ran; our contract draft was wrong, not the code
eidoslab/neq/src/Swin-Transformer/logger.py
pointer only (licence: MIT); the stored copy get_code serves, from ghrua/seqpe, is pointer only (licence: NONE) · get_code("80450600f7f09b0a")
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 ghrua/seqpe, 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.

criterion Ran
ran on a synthesized input
eidoslab/neq/src/train_segmentation.py
code served (permissive licence) · get_code("d6c803410533ccf3")
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 as nn

torch.manual_seed(0)

# The function expects:
# - inputs: dict with keys like 'out' and 'aux', values are tensors for cross_entropy
# - target: tensor of class indices

# cross_entropy expects:
# - input: (N, C) where N is batch size, C is number of classes
# - target: (N,) with class indices

batch_size = 2
num_classes = 4

# Create inputs dict with 'out' and 'aux' keys
# Each value should be logits of shape (batch_size, num_classes)
inputs = {
    'out': torch.randn(batch_size, num_classes),
    'aux': torch.randn(batch_size, num_classes)
}

# Create target tensor with class indices
# Use values in range [0, num_classes) and 255 for ignore_index
target = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    'inputs': inputs,
    'target': target
}
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
evaleps Ran
ran on a synthesized input
eidoslab/neq/src/classification/arg_parser.py
code served (permissive licence) · get_code("40bb865fc015a2f7")
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 str. 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

def evaleps(i):
    if i == 'none':
        return 'none'
    else:
        return float(i)

ARGS = {
    'i': 'none'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
find_module_by_name Ran
ran on a synthesized input
eidoslab/neq/src/general_utils.py
code served (permissive licence) · get_code("0afbb1170c111007")
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 Linear. 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.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
        self.submodule = nn.Sequential(
            nn.Linear(2, 5),
            nn.ReLU()
        )
    
    def forward(self, x):
        return x

model = SimpleModel()

ARGS = {
    "model": model,
    "name": "layer1"
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
get_grad_norm Ran
ran, honoured the contract we drafted
eidoslab/neq/src/Swin-Transformer/utils.py
code served (permissive licence) · get_code("eec1e7cba51d5e8e")
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 float, 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 as nn

torch.manual_seed(0)

# Create a simple model with parameters that have gradients
model = nn.Linear(4, 3)

# Forward pass to create some gradients
x = torch.randn(2, 4)
y = model(x)
loss = y.sum()
loss.backward()

# Now model.parameters() have gradients attached
parameters = list(model.parameters())

ARGS = {
    "parameters": parameters,
    "norm_type": 2
}
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 float, 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
int2bool Ran
ran on a synthesized input
eidoslab/neq/src/classification/arg_parser.py
code served (permissive licence) · get_code("0927b0d3598a4e88")
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 bool, 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

def int2bool(i):
    i = int(i)
    assert i == 0 or i == 1
    return i == 1

ARGS = {
    "i": 1
}
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 bool, 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
load_checkpoint Ran
ran on a synthesized input
eidoslab/neq/src/Swin-Transformer/utils.py
code served (permissive licence) · get_code("640408a0715e42c2")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 as nn
from unittest.mock import Mock, MagicMock
import logging

torch.manual_seed(0)

# Create a minimal model
class TinyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = TinyModel()

# Create optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create lr_scheduler
lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10)

# Create a mock config with required attributes
class Config:
    def __init__(self):
        self.MODEL = Mock()
        self.MODEL.RESUME = '/tmp/checkpoint.pth'
        self.EVAL_MODE = True
        self.AMP_OPT_LEVEL = 'O0'
        self.TRAIN = Mock()
        self.TRAIN.START_EPOCH = 0
        self._frozen = False
    
    def defrost(self):
        self._frozen = False
    
    def freeze(self):
        self._frozen = True

config = Config()

# Create a mock logger
logger = Mock(spec=logging.Logger)
logger.info = MagicMock()

# Create a checkpoint file (mock by using torch.save)
checkpoint_data = {
    'model': model.state_dict(),
    'optimizer': optimizer.state_dict(),
    'lr_scheduler': lr_scheduler.state_dict(),
    'epoch': 5,
    'max_accuracy': 0.95,
    'config': config,
    'amp': {}
}

# Since we can't do real file I/O, we'll mock torch.load
original_torch_load = torch.load
def mock_torch_load(path, map_location=None):
    return checkpoint_data

torch.load = mock_torch_load

ARGS = {
    'config': config,
    'model': model,
    'optimizer': optimizer,
    'lr_scheduler': lr_scheduler,
    'logger': logger
}
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 float, 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
set_weight_decay Ran
ran on a synthesized input
eidoslab/neq/src/Swin-Transformer/optimizer.py
code served (permissive licence) · get_code("d54a6d0b660e3b69")
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 list, ndim 1, dtype family float; 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
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model with various parameter types
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        # 2D weight (will have decay)
        self.linear1 = nn.Linear(4, 3)
        # 1D bias (no decay - len(param.shape) == 1)
        self.linear2 = nn.Linear(3, 2)
        # Another layer to have more parameters
        self.linear3 = nn.Linear(2, 1)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)
        return x

model = SimpleModel()

# Create test arguments
ARGS = {
    'model': model,
    'skip_list': ('linear3.weight',),  # Skip this parameter by name
    'skip_keywords': ('bias',)  # Skip parameters with 'bias' in their name
}
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 list, ndim 1, dtype family float — a list 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
split_dataset Ran
ran on a synthesized input
eidoslab/neq/src/general_utils.py
code served (permissive licence) · get_code("57dd477e8805987e")
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. 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 torch.utils.data import Dataset

torch.manual_seed(0)

# Create a minimal custom dataset
class SimpleDataset(Dataset):
    def __init__(self, size=10):
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(4), torch.randint(0, 2, (1,))

# Construct the dataset
dataset = SimpleDataset(size=10)

# Define ARGS dict with all parameters
ARGS = {
    "dataset": dataset,
    "percentage": 0.3,
    "random_seed": 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
topk_accuracy Ran
ran on a synthesized input
eidoslab/neq/src/classification/fit.py
code served (permissive licence) · get_code("0af9112ff1be740b")
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 float, 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 testing
batch_size = 2
num_classes = 4

# outputs: shape (batch_size, num_classes) - logits that will be softmaxed
outputs = torch.randn(batch_size, num_classes)

# labels: shape (batch_size,) - class indices
labels = torch.tensor([0, 2])

# topk: number of top predictions to consider
topk = 1

ARGS = {
    "outputs": outputs,
    "labels": labels,
    "topk": topk,
}
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 float, 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
get_config Not yet run
unverified (harvested, no recorded run)
eidoslab/neq/src/Swin-Transformer/config.py
code served (permissive licence) · get_code("9b9b6364be5f95f6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 6 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.

FunctionAlso present inEarliest-datedOthers named
get_config 51 other papers
11 dated earlier, 39 later, 1 same year, order not determinable
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 48 more not named here
create_logger 35 other papers
8 dated earlier, 26 later, 1 same year, order not determinable
2104.13840 (2021-04)
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 32 more not named here
check_keywords_in_name 31 other papers
7 dated earlier, 24 later
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
and 28 more not named here
get_grad_norm 23 other papers
6 dated earlier, 17 later
1910.13616 (2019-10)
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
and 20 more not named here
auto_resume_helper 20 other papers
5 dated earlier, 15 later
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.04263 (2021-06)
On the Connection between Local Attention and Dynamic Depth-wise Convolution
and 17 more not named here
build_scheduler 13 other papers
7 dated earlier, 5 later, 1 same year, order not determinable
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2106.03746 (2021-06)
Efficient Training of Visual Transformers with Small Datasets
2106.04263 (2021-06)
On the Connection between Local Attention and Dynamic Depth-wise Convolution
and 10 more not named here
load_checkpoint 2 other papers
2 dated earlier
2106.03650 (2021-06)
Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer
2107.08391 (2021-07)
AS-MLP: An Axial Shifted MLP Architecture for Vision

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

Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply training a subset of their parameters. Such a discovery has a broad impact from theory to applications, driving the research towards methods to identify the minimum subset of parameters to train without look-ahead information exploitation. However, the methods proposed do not match the state-of-the-art performance, and rely on unstructured sparsely connected models. In this work we shift our focus from the single parameters to the behavior of the whole neuron, exploiting the concept of neuronal equilibrium (NEq). When a neuron is in a configuration at equilibrium (meaning that it has learned a specific input-output relationship), we can halt its update; on the contrary, when a neuron is at non-equilibrium, we let its state evolve towards an equilibrium state, updating its parameters. The proposed approach has been tested on different state-of-the-art learning strategies and tasks, validating NEq and observing that the neuronal equilibrium depends on the specific learning setup.

For agents

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

get_harvested_code_for_paper("2207.09455")
get_code_for_paper("2207.09455")
have("2207.09455")

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

curl https://syntology.ai/api/ran/2207.09455.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.09455.svg)](https://syntology.ai/paper/2207.09455)

Connect an agent — have() is free.