SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.03048 · 2024

Latte: Latent Diffusion Transformer for Video Generation

arXiv · PDF · Open in the Atlas

Code that ran

12 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 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/2401.03048.json · badge: /api/ran/2401.03048.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
maxin-cn/Latte canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
clip_grad_norm_ Ran
ran, honoured the contract we drafted
maxin-cn/Latte/utils.py
code served (permissive licence) · get_code("72ee7e991255ed28")
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)

# Create tensor parameters with gradients
param1 = torch.randn(2, 4, requires_grad=True)
param2 = torch.randn(3, 5, requires_grad=True)

# Simulate a backward pass to create gradients
loss1 = param1.sum()
loss1.backward()

loss2 = param2.sum()
loss2.backward()

# Define ARGS dictionary with all parameters
ARGS = {
    "parameters": [param1, param2],
    "max_norm": 1.0,
    "norm_type": 2.0,
    "error_if_nonfinite": False,
    "clip_grad": True,
}
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
create_logger Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/train_pl.py
code served (permissive licence) · get_code("ea2dc93d273c536c")
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 Logger. 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 logging

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

# Define arguments for create_logger
ARGS = {
    'logging_dir': temp_dir
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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_1d_sincos_temp_embed Ran
ran, honoured the contract we drafted
maxin-cn/Latte/models/latte.py
code served (permissive licence) · get_code("c8dc321d086803c8")
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 ndarray, ndim 2, dtype family float, shape (4, 8) 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 numpy as np

torch.manual_seed(0)

ARGS = {
    "embed_dim": 8,
    "length": 4,
}
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 ndarray, ndim 2, dtype family float, shape (4, 8) — shape (4, 8) 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_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
maxin-cn/Latte/models/latte.py
code served (permissive licence) · get_code("c92c27c924b517e8")
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 ndarray, ndim 2, dtype family float, shape (18, 8) 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 numpy as np

# Define ARGS dict with all parameters for get_2d_sincos_pos_embed
ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": True,
    "extra_tokens": 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (18, 8) — shape (18, 8) 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_experiment_dir Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/utils.py
code served (permissive licence) · get_code("f2b6bc25cb2bbec8")
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
import numpy as np

class Args:
    def __init__(self):
        self.use_compile = True
        self.fixed_spatial = False
        self.enable_xformers_memory_efficient_attention = True
        self.gradient_checkpointing = False
        self.mixed_precision = True
        self.image_size = 512

args = Args()
root_dir = '/experiments/model'

ARGS = {
    'root_dir': root_dir,
    'args': args
}
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 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
get_filelist Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/datasets/ffs_datasets.py
code served (permissive licence) · get_code("8c9a5a9b54bc8e33")
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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
subdir1 = os.path.join(temp_dir, "subdir1")
subdir2 = os.path.join(temp_dir, "subdir2")
os.makedirs(subdir1)
os.makedirs(subdir2)

# Create some test files
open(os.path.join(temp_dir, "file1.txt"), "w").close()
open(os.path.join(temp_dir, "file2.txt"), "w").close()
open(os.path.join(subdir1, "file3.txt"), "w").close()
open(os.path.join(subdir2, "file4.txt"), "w").close()

ARGS = {
    "file_path": temp_dir
}
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 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
get_grad_norm Ran
ran, honoured the contract we drafted
maxin-cn/Latte/utils.py
code served (permissive licence) · get_code("64900e821beadb4e")
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)

# Create a simple model with parameters that have gradients
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

# Create model and compute gradients
model = SimpleModel()
x = torch.randn(2, 4)
y = torch.randn(2, 2)
output = model(x)
loss = ((output - y) ** 2).sum()
loss.backward()

# Extract parameters with gradients
parameters_with_grads = [p for p in model.parameters() if p.grad is not None]

# Define arguments for the function
ARGS = {
    "parameters": parameters_with_grads,
    "norm_type": 2.0
}
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
modulate Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/models/latte.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
numpy2tensor Ran
ran, honoured the contract we drafted
maxin-cn/Latte/datasets/ffs_datasets.py
code served (permissive licence) · get_code("b76cb2065bce9c3e")
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
import numpy as np

torch.manual_seed(0)

# The function takes a numpy array and converts it to a tensor
# We need to provide a valid numpy array
x = np.array([[1.0, 2.0, 3.0, 4.0],
              [5.0, 6.0, 7.0, 8.0]], dtype=np.float32)

ARGS = {
    'x': x
}
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 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
temporal_sampling Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/datasets/ffs_datasets.py
code served (permissive licence) · get_code("2ce6782a49b98214")
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 (5, 3, 4, 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 tensor of video frames: num_frames x channels x height x width
frames = torch.randn(10, 3, 4, 4)

start_idx = 0
end_idx = 9
num_samples = 5

ARGS = {
    "frames": frames,
    "start_idx": start_idx,
    "end_idx": end_idx,
    "num_samples": num_samples,
}
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 (5, 3, 4, 4) — shape (5, 3, 4, 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
timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
maxin-cn/Latte/models/utils.py
code served (permissive licence) · get_code("319f00691ca1b97c")
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
import math
from einops import repeat

torch.manual_seed(0)

# Construct arguments for timestep_embedding function
timesteps = torch.tensor([0, 1], dtype=torch.int64)  # 1-D tensor with 2 batch elements
dim = 4  # output dimension
max_period = 10000  # controls minimum frequency
repeat_only = False  # use sinusoidal embeddings, not repeat mode

ARGS = {
    "timesteps": timesteps,
    "dim": dim,
    "max_period": max_period,
    "repeat_only": repeat_only
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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
zero_module Ran
ran; our contract draft was wrong, not the code
maxin-cn/Latte/models/utils.py
code served (permissive licence) · get_code("129b804760b3115f")
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 SimpleModule. 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 module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 2, 3)
    
    def forward(self, x):
        return x

module = SimpleModule()

# Verify the module has non-zero parameters before zeroing
for p in module.parameters():
    assert p.abs().sum() > 0, "Parameters should be non-zero initially"

ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
checkpoint Not yet run
unverified (harvested, no recorded run)
maxin-cn/Latte/models/utils.py
code served (permissive licence) · get_code("6fe195fcfd10e259")
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, 10 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 7 the same month, 9 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
zero_module 196 other papers
92 dated earlier, 3 the same month, 100 later, 1 same year, order not determinable · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
modulate 101 other papers
11 dated earlier, 4 the same month, 85 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
get_2d_sincos_pos_embed 69 other papers
9 dated earlier, 4 the same month, 56 later · 12 only as an assembly brick
2203.10897 (2022-03)
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
2212.09748 (2022-12)
Scalable Diffusion Models with Transformers
2303.14389 (2023-03)
Masked Diffusion Transformer is a Strong Image Synthesizer
and 66 more not named here
checkpoint 51 other papers
27 dated earlier, 2 the same month, 22 later · 29 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 48 more not named here
temporal_sampling 4 other papers
4 dated earlier
2005.03788 (2020-05)
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
136950157 (2022 (year only))
K-centered Patch Sampling for Efficient Video Recognition
and 1 more not named here
timestep_embedding 4 other papers
1 dated earlier, 1 the same month, 2 later
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
2401.09414 (2024-01)
Vlogger: Make Your Dream A Vlog
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
and 1 more not named here
get_1d_sincos_temp_embed 3 other papers
3 later
2407.14651 (2024-07)
Improving Representation of High-frequency Components for Medical Visual Foundation Models
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
2411.17616 (2024-11)
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
clip_grad_norm_ 2 other papers
1 the same month, 1 later
2401.09414 (2024-01)
Vlogger: Make Your Dream A Vlog
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
get_grad_norm 2 other papers
1 the same month, 1 later
2401.09414 (2024-01)
Vlogger: Make Your Dream A Vlog
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
get_experiment_dir 1 other paper
1 later
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

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 propose Latte, a novel Latent Diffusion Transformer for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to the text-to-video generation (T2V) task, where Latte achieves results that are competitive with recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.

For agents

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

get_harvested_code_for_paper("2401.03048")
get_code_for_paper("2401.03048")
have("2401.03048")

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

curl https://syntology.ai/api/ran/2401.03048.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.03048.svg)](https://syntology.ai/paper/2401.03048)

Connect an agent — have() is free.