SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12376 · 2024

FiT: Flexible Vision Transformer for Diffusion Model

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 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/2402.12376.json · badge: /api/ran/2402.12376.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
whlzy/fit canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/scheduler/improved_diffusion/diffusion_utils.py
code served (permissive licence) · get_code("d6a68e210556f857")
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 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 as th
import numpy as np

th.manual_seed(0)

# The function takes a single parameter 'x' which should be a torch tensor
# It performs mathematical operations on it: tanh, pow, addition, multiplication
# So x should be a tensor of any shape

x = th.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
continuous_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/scheduler/improved_diffusion/diffusion_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rerv/vdt, is pointer only (licence: NOASSERTION) · get_code("ab1c9568b4e13899")
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 rerv/vdt, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

create_norm Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/model/norms.py
code served (permissive licence) · get_code("85ccfb32256956d8")
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 RMSNorm. 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)

ARGS = {
    "norm_type": "w_rmsnorm",
    "dim": 8,
    "eps": 1e-6,
}
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 RMSNorm — a RMSNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RMSNorm 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
create_npz_from_sample_folder Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/eval_utils.py
code served (permissive licence) · get_code("7a6ba78116641182")
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 os
import tempfile
import numpy as np
from PIL import Image

# Create a temporary directory with sample PNG files
temp_dir = tempfile.mkdtemp()

# Create 100 small PNG images (we only need 50 for the function, but creating extra)
# Each image is 8x6 RGB (3 channels)
for i in range(100):
    img_array = np.random.randint(0, 256, (8, 6, 3), dtype=np.uint8)
    img = Image.fromarray(img_array, mode='RGB')
    img.save(os.path.join(temp_dir, f'{i}.png'))

ARGS = {
    'sample_dir': temp_dir,
    'num': 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, tqdm — 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_correction_factor Ran
ran, honoured the contract we drafted
whlzy/fit/fit/model/rope.py
code served (permissive licence) · get_code("191c81a96b555436")
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 math

# Analyze the function signature and body
# Parameters:
# - num_rotations: used in division (numeric)
# - dim: used in multiplication (numeric)
# - base: used in math.log (numeric, default 10000)
# - max_position_embeddings: used in division (numeric, default 2048)

# The function performs mathematical calculations with these numeric parameters
# No special objects or models are needed

ARGS = {
    "num_rotations": 8,
    "dim": 64,
    "base": 10000,
    "max_position_embeddings": 2048
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
find_correction_range Ran
ran, honoured the contract we drafted
whlzy/fit/fit/model/rope.py
code served (permissive licence) · get_code("b4a38f39f9288869")
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 math

# Analyze the function find_correction_range:
# It takes parameters: low_rot, high_rot, dim, base, max_position_embeddings
# It calls find_correction_factor twice with (low_rot, dim, base, max_position_embeddings)
# and (high_rot, dim, base, max_position_embeddings)
# Then it uses math.floor and math.ceil on the results
# Finally it returns a tuple with max(low, 0) and min(high, dim - 1)

# All parameters are numeric (int or float)
# Let's construct valid arguments:

low_rot_val = 1.0  # rotation value
high_rot_val = 10.0  # higher rotation value
dim_val = 64  # embedding dimension
base_val = 10000  # base for position encoding
max_position_embeddings_val = 2048  # max sequence length

ARGS = {
    "low_rot": low_rot_val,
    "high_rot": high_rot_val,
    "dim": dim_val,
    "base": base_val,
    "max_position_embeddings": max_position_embeddings_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
get_constant_schedule Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/lr_scheduler.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Feng-Hong/WINO-DLLM, is pointer only (licence: NONE) · get_code("a8366f238618edad")
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 Feng-Hong/WINO-DLLM, 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.

get_constant_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/lr_scheduler.py
code served (permissive licence) · get_code("5e2efd2c5b6288c6")
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 LambdaLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a minimal model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define arguments
ARGS = {
    "optimizer": optimizer,
    "num_warmup_steps": 100,
    "div_factor": 0.0001,
    "last_epoch": -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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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_obj_from_str Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/utils.py
code served (permissive licence) · get_code("30d11b7b4428ab6e")
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 type. 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 importlib
import torch
import torch.nn as nn

torch.manual_seed(0)

# The function get_obj_from_str takes a string like "module.path.ClassName"
# and returns the class/object from that module.
# It uses: string (rsplit), reload (bool), invalidate_cache (bool)
# and calls: importlib.invalidate_caches(), importlib.import_module(), 
# importlib.reload(), getattr()

# We need to provide a valid string that points to an actual importable class
# Let's use a built-in class that's guaranteed to exist
string_value = "torch.nn.modules.linear.Linear"

ARGS = {
    "string": string_value,
    "reload": False,
    "invalidate_cache": 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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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_parameter_dtype Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/model/utils.py
code served (permissive licence) · get_code("1d8274f9142363e1")
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 dtype. 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)

# Create a simple nn.Module with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Test case 1: Module with parameters
model_with_params = SimpleModel()

# Test case 2: Module with buffers but no parameters
class ModelWithBuffers(nn.Module):
    def __init__(self):
        super().__init__()
        self.register_buffer('my_buffer', torch.tensor([1.0, 2.0, 3.0, 4.0]))
    
    def forward(self, x):
        return x

model_with_buffers = ModelWithBuffers()

# Test case 3: Module with tensor attributes (for the find_tensor_attributes path)
class ModelWithTensorAttrs(nn.Module):
    def __init__(self):
        super().__init__()
        self.tensor_attr = torch.tensor([1.0, 2.0, 3.0, 4.0])
    
    def forward(self, x):
        return x

model_with_tensor_attrs = ModelWithTensorAttrs()

ARGS = {
    "parameter": model_with_params
}
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 dtype — a dtype output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dtype 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_piecewise_constant_schedule Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/lr_scheduler.py
code served (permissive licence) · get_code("9cc5235bd8b13556")
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 LambdaLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define step_rules string following the format described in the docstring
# Format: "multiplier1:steps1,multiplier2:steps2,...,multiplier_n:steps_n,final_multiplier"
# Example: "1:10,0.1:20,0.01:30,0.005"
step_rules = "1:10,0.1:20,0.01:30,0.005"

# Define last_epoch
last_epoch = -1

ARGS = {
    "optimizer": optimizer,
    "step_rules": step_rules,
    "last_epoch": last_epoch,
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
instantiate_from_config Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/utils/utils.py
code served (permissive licence) · get_code("18d8fb19d766c90f")
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
import importlib

torch.manual_seed(0)

# Create a simple test module and class for the string resolution
class SimpleModule(nn.Module):
    def __init__(self, param1=10, param2=20):
        super().__init__()
        self.param1 = param1
        self.param2 = param2

# Create a config that points to a built-in class that can be instantiated
config_with_target = {
    'target': 'torch.nn.Linear',
    'params': {
        'in_features': 4,
        'out_features': 3
    }
}

config_special_first_stage = '__is_first_stage__'

config_special_unconditional = '__is_unconditional__'

config_without_target = {
    'param1': 10,
    'param2': 20
}

ARGS = {
    'config': config_with_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 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
linear_ramp_mask Ran
ran, honoured the contract we drafted
whlzy/fit/fit/model/rope.py
code served (permissive licence) · get_code("5034871c1d2783cf")
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 (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)

ARGS = {
    "min": 2.0,
    "max": 8.0,
    "dim": 4
}
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 (4,) — shape (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
modulate Ran
ran; our contract draft was wrong, not the code
whlzy/fit/fit/model/utils.py
code served (permissive licence) · get_code("03310bba324ae4fb")
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 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 small tensors for the modulate function
# x: input tensor with shape (batch_size, feature_dim)
x = torch.randn(2, 4)

# shift: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
shift = torch.randn(2)

# scale: tensor that will be unsqueezed to (batch_size, 1)
# so it should have shape (batch_size,)
scale = torch.randn(2)

ARGS = {
    "x": x,
    "shift": shift,
    "scale": scale,
}
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 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
normal_kl Ran
ran, honoured the contract we drafted
whlzy/fit/fit/scheduler/improved_diffusion/diffusion_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rerv/vdt, is pointer only (licence: NOASSERTION) · get_code("8afbfc42c6ea0448")
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 rerv/vdt, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

default Not yet run
unverified (harvested, no recorded run)
whlzy/fit/fit/utils/utils.py
code served (permissive licence) · get_code("f573c816626189bc")
How it ran

no invocation recorded.

none_or_str Not yet run
unverified (harvested, no recorded run)
whlzy/fit/fit/utils/sit_eval_utils.py
code served (permissive licence) · get_code("2fc6fdb85f13dc41")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 14 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 5 the same month, 10 later) and 3 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
default 207 other papers
124 dated earlier, 5 the same month, 72 later, 6 same year, order not determinable · 41 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.08162 (2020-10)
SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning
and 204 more not named here
normal_kl 160 other papers
81 dated earlier, 9 the same month, 68 later, 2 same year, order not determinable · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
approx_standard_normal_cdf 154 other papers
77 dated earlier, 8 the same month, 67 later, 2 same year, order not determinable · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
modulate 101 other papers
16 dated earlier, 4 the same month, 80 later, 1 undated · 29 only as an assembly brick
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
and 98 more not named here
continuous_gaussian_log_likelihood 26 other papers
3 dated earlier, 2 the same month, 20 later, 1 same year, order not determinable
2305.13311 (2023-05)
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
2306.14770 (2023-06)
ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
2312.02139 (2023-12)
DiffiT: Diffusion Vision Transformers for Image Generation
and 23 more not named here
instantiate_from_config 24 other papers
11 dated earlier, 13 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
and 21 more not named here
none_or_str 16 other papers
6 dated earlier, 10 later
1810.01845 (2018-10)
Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation
1909.10893 (2019-09)
Recurrent Independent Mechanisms
2109.11251 (2021-09)
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
and 13 more not named here
get_constant_schedule 13 other papers
5 dated earlier, 7 later, 1 same year, order not determinable
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2204.13902 (2022-04)
Fast Sampling of Diffusion Models with Exponential Integrator
2305.15328 (2023-05)
Visual Programming for Text-to-Image Generation and Evaluation
and 10 more not named here
linear_ramp_mask 4 other papers
1 dated earlier, 3 later
2312.15166 (2023-12)
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
2404.10308 (2024-04)
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
2404.12224 (2024-04)
Length Generalization of Causal Transformers without Position Encoding
and 1 more not named here
get_obj_from_str 2 other papers
2 later
2405.13870 (2024-05)
FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
2405.17398 (2024-05)
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
find_correction_factor 1 other paper
1 dated earlier
2312.15166 (2023-12)
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
find_correction_range 1 other paper
1 dated earlier
2312.15166 (2023-12)
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
get_parameter_dtype 1 other paper
1 dated earlier
2310.10640 (2023-10)
LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
get_piecewise_constant_schedule 1 other paper
1 dated earlier
2401.15636 (2024-01)
FreeStyle: Free Lunch for Text-guided Style Transfer using Diffusion Models

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

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. This perspective enables a flexible training strategy that effortlessly adapts to diverse aspect ratios during both training and inference phases, thus promoting resolution generalization and eliminating biases induced by image cropping. Enhanced by a meticulously adjusted network structure and the integration of training-free extrapolation techniques, FiT exhibits remarkable flexibility in resolution extrapolation generation. Comprehensive experiments demonstrate the exceptional performance of FiT across a broad range of resolutions, showcasing its effectiveness both within and beyond its training resolution distribution. Repository available at https://github.com/whlzy/FiT.

For agents

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

get_harvested_code_for_paper("2402.12376")
get_code_for_paper("2402.12376")
have("2402.12376")

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

curl https://syntology.ai/api/ran/2402.12376.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.12376.svg)](https://syntology.ai/paper/2402.12376)

Connect an agent — have() is free.