SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09414 · CVPR · 2024

Vlogger: Make Your Dream A Vlog

Ziwei Liu, Chen, Yu Qiao, Kunchang Li, Yali Wang, Yaohui Wang, Shaobin Zhuang

arXiv · PDF · Open in the Atlas

Code that ran

8 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 7 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/2401.09414.json · badge: /api/ran/2401.09414.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
zhuangshaobin/vlogger canonical (classifier label)
classifier basis: census
8 ran · 7 no recorded run
FunctionStatusWhere it lives
clip_grad_norm_ Ran
ran, honoured the contract we drafted
zhuangshaobin/vlogger/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
exists Ran
ran, violated the contract we drafted
zhuangshaobin/vlogger/models/attention.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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 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 exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
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 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
fetch_files_by_numbers Ran
ran; our contract draft was wrong, not the code
zhuangshaobin/vlogger/utils.py
code served (permissive licence) · get_code("883136012250a325")
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.

# Analyze the function to understand what arguments are needed
# fetch_files_by_numbers(start_number, count, file_list)
# - start_number: integer, the starting number
# - count: integer, how many files to fetch
# - file_list: list of filenames that end with padded numbers + '.csv'

# The function creates file_numbers using range(start_number, start_number + count)
# Then it looks for files in file_list that end with the padded number + '.csv'

# Create sample file names that match the expected pattern
file_list = [
    'data_00.csv',
    'data_01.csv',
    'data_02.csv',
    'data_03.csv',
    'data_04.csv',
    'log_05.csv',
    'report_10.csv',
]

start_number = 1
count = 3

ARGS = {
    'start_number': start_number,
    'count': count,
    'file_list': file_list,
}
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
zhuangshaobin/vlogger/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
ip_scale_set Ran
ran; our contract draft was wrong, not the code
zhuangshaobin/vlogger/vlogger/STEB/model_transform.py
code served (permissive licence) · get_code("3c6d7b87fb5bde2d")
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 SimpleModel. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class ScalableAttention(nn.Module):
    def __init__(self):
        super().__init__()
        self.scale = 1.0
    
    def set_scale(self, scale):
        self.scale = scale

class TransformerBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.attn2 = ScalableAttention()

class AttentionModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.transformer_blocks = nn.ModuleList([TransformerBlock()])

class Block(nn.Module):
    def __init__(self, num_attentions=2):
        super().__init__()
        self.attentions = nn.ModuleList([AttentionModule() for _ in range(num_attentions)])

class MidBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.attentions = nn.ModuleList([AttentionModule() for _ in range(1)])

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.down_blocks = nn.ModuleList([Block(num_attentions=2), Block(num_attentions=2)])
        self.mid_block = MidBlock()
        self.up_blocks = nn.ModuleList([Block(num_attentions=2), Block(num_attentions=2)])

model = SimpleModel()
scale = 0.5

ARGS = {
    "model": model,
    "scale": scale
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tca_transform_model Ran
ran; our contract draft was wrong, not the code
zhuangshaobin/vlogger/vlogger/STEB/model_transform.py
code served (permissive licence) · get_code("b0c0346a19941385")
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 Model. 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 TransformerBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def tca_transform(self):
        pass

class Attention(nn.Module):
    def __init__(self):
        super().__init__()
        self.transformer_blocks = nn.ModuleList([TransformerBlock()])

class DownBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.attentions = nn.ModuleList([Attention()])

class MidBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.attentions = nn.ModuleList([Attention()])

class UpBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.attentions = nn.ModuleList([Attention()])

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.down_blocks = nn.ModuleList([DownBlock()])
        self.mid_block = MidBlock()
        self.up_blocks = nn.ModuleList([UpBlock()])

model = Model()

ARGS = {
    "model": model
}
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 Model — a Model output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Model 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
timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhuangshaobin/vlogger/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
zhuangshaobin/vlogger/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
ExtractAProtagonist Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/vlogger/planning_utils/gpt4_utils.py
code served (permissive licence) · get_code("6378e01f958e191e")
How it ran

no invocation recorded.

ExtractProtagonist Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/vlogger/planning_utils/gpt4_utils.py
code served (permissive licence) · get_code("d3caeee440b6a2e6")
How it ran

no invocation recorded.

checkpoint Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/models/utils.py
code served (permissive licence) · get_code("6fe195fcfd10e259")
How it ran

no invocation recorded.

get_down_block Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/models/unet_blocks.py
code served (permissive licence) · get_code("789d775e0126423b")
How it ran

no invocation recorded.

get_up_block Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/models/unet_blocks.py
code served (permissive licence) · get_code("3ae6e2960734d721")
How it ran

no invocation recorded.

ip_transform_model Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/vlogger/STEB/model_transform.py
code served (permissive licence) · get_code("5ccc98c72e659c92")
How it ran

no invocation recorded.

json_completion Not yet run
unverified (harvested, no recorded run)
zhuangshaobin/vlogger/vlogger/planning_utils/gpt4_utils.py
code served (permissive licence) · get_code("5b8534688e637365")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 6 the same month, 6 later) and 7 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
exists 144 other papers
68 dated earlier, 2 the same month, 69 later, 5 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 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
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
2401.03048 (2024-01)
Latte: Latent Diffusion Transformer for Video Generation
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
and 1 more not named here
clip_grad_norm_ 2 other papers
1 the same month, 1 later
2401.03048 (2024-01)
Latte: Latent Diffusion Transformer for Video Generation
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
2401.03048 (2024-01)
Latte: Latent Diffusion Transformer for Video Generation
2410.03160 (2024-10)
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
get_down_block 1 other paper
1 dated earlier
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
get_up_block 1 other paper
1 dated earlier
2310.15169 (2023-10)
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

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

In this work, we present Vlogger, a generic AI system for generating a minute-level video blog (i.e., vlog) of user descriptions. Different from short videos with a few seconds, vlog often contains a complex storyline with diversified scenes, which is challenging for most existing video generation approaches. To break through this bottleneck, our Vlogger smartly leverages Large Language Model (LLM) as Director and decomposes a long video generation task of vlog into four key stages, where we invoke various foundation models to play the critical roles of vlog professionals, including (1) Script, (2) Actor, (3) ShowMaker, and (4) Voicer. With such a design of mimicking human beings, our Vlogger can generate vlogs through explainable cooperation of top-down planning and bottom-up shooting. Moreover, we introduce a novel video diffusion model, Show-Maker, which serves as a videographer in our Vlogger for generating the video snippet of each shooting scene. By incorporating Script and Actor attentively as textual and visual prompts, it can effectively enhance spatial-temporal coherence in the snippet. Besides, we design a concise mixed training paradigm for ShowMaker, boosting its capacity for both T2V generation and prediction. Finally, the extensive experiments show that our method achieves stateof-the-art performance on zero-shot T2V generation and prediction tasks. More importantly, Vlogger can generate over 5-minute vlogs from open-world descriptions, without loss of video coherence on script and actor.

For agents

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

get_harvested_code_for_paper("2401.09414")
get_code_for_paper("2401.09414")
have("2401.09414")

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

curl https://syntology.ai/api/ran/2401.09414.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09414.svg)](https://syntology.ai/paper/2401.09414)

Connect an agent — have() is free.