SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.10076 · 2024

VideoAgent: Self-Improving Video Generation

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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, 4 violated it and 1 has no contract verdict; 5 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2410.10076.json · badge: /api/ran/2410.10076.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
video-as-agent/videoagent canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
identity Ran
ran, honoured the contract we drafted
video-as-agent/videoagent/flowdiffusion/model/imagen.py
code served (permissive licence) · get_code("7f1040f5e3991d5e")
How it ran

Ran in Syntology's jail 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. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:37:21Z). 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 identity function simply returns its first argument
# and ignores all other args and kwargs
# So we need to provide a value for t and can optionally provide other args/kwargs

t = torch.randn(2, 4)
extra_arg_1 = torch.randn(3, 5)
extra_arg_2 = "some_string"
extra_kwarg_1 = 42
extra_kwarg_2 = [1, 2, 3]

ARGS = {
    "t": t,
    "args": (extra_arg_1, extra_arg_2),
    "kwargs": {"key1": extra_kwarg_1, "key2": extra_kwarg_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 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
adaptive_sampling Ran
ran on a synthesized input
video-as-agent/videoagent/sample_dataset_generation.py
code served (permissive licence) · get_code("d3c3fae976f3a679")
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 2, 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 numpy as np

torch.manual_seed(0)

# The function takes:
# - seq: a sequence that supports indexing (list or tensor-like)
# - start_frame_idx: integer
# - last_frame_idx: integer
# - total_frames: integer (appears unused in function body)
# - sample_per_seq: integer with default 8

# Create a simple sequence (list of items that can be indexed)
# We'll make it a list of small tensors to be realistic
seq = [torch.randn(4) for _ in range(50)]

# Define frame indices
start_frame_idx = 5
last_frame_idx = 45
total_frames = 50
sample_per_seq = 8

ARGS = {
    "seq": seq,
    "start_frame_idx": start_frame_idx,
    "last_frame_idx": last_frame_idx,
    "total_frames": total_frames,
    "sample_per_seq": sample_per_seq,
}
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 list, ndim 2, 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
default Ran
ran, violated the contract we drafted
video-as-agent/videoagent/flowdiffusion/goal_diffusion.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
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 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

torch.manual_seed(0)

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

# Test case 1: val is not None, should return val
val_1 = "test_value"
d_1 = lambda: "default_value"

# Test case 2: val is None, d is callable, should return d()
val_2 = None
d_2 = lambda: "computed_default"

# Test case 3: val is None, d is not callable, should return d
val_3 = None
d_3 = "static_default"

# Test case 4: val is a number
val_4 = 42
d_4 = 100

# Test case 5: val is a tensor
val_5 = torch.tensor([1.0, 2.0, 3.0])
d_5 = lambda: torch.tensor([0.0])

ARGS = {
    "val": val_1,
    "d": d_1
}
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 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
downsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
video-as-agent/videoagent/flowdiffusion/model/resnet.py
code served (permissive licence) · get_code("f46bcb6099334fa6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 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 small batch of 2D images with shape [N, C, H, W]
# N=2 (batch size), C=3 (channels), H=8 (height), W=8 (width)
hidden_states = torch.randn(2, 3, 8, 8)

# Create a kernel - can be 1D or 2D
# Using a simple 1D kernel that will be converted to 2D via outer product
kernel = [1, 1]

# Downsampling factor
factor = 2

# Gain scaling factor
gain = 1.0

ARGS = {
    "hidden_states": hidden_states,
    "kernel": kernel,
    "factor": factor,
    "gain": gain,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 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
encode_gif Ran
ran; our contract draft was wrong, not the code
video-as-agent/videoagent/flowdiffusion/feedback_binary_rf.py
code served (permissive licence) · get_code("42b1783a347ad0d9")
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.

from PIL import Image
import tempfile
import os

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

# Create a simple test image (single frame static image)
test_image_path = os.path.join(temp_dir, "test_image.png")
img = Image.new('RGB', (100, 100), color='red')
img.save(test_image_path)

# Create a simple animated GIF for testing
gif_path = os.path.join(temp_dir, "test_animation.gif")
frames = []
for i in range(3):
    frame = Image.new('RGB', (100, 100), color=(i*80, 0, 0))
    frames.append(frame)
frames[0].save(gif_path, save_all=True, append_images=frames[1:], duration=100, loop=0)

ARGS = {
    "image_path": gif_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — 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
encode_image Ran
ran; our contract draft was wrong, not the code
video-as-agent/videoagent/flowdiffusion/feedback_binary_rf.py
pointer only (licence: MIT); the stored copy get_code serves, from jongwoopark7978/LVNet, is pointer only (licence: NONE) · get_code("f41cb1a19b154297")
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 jongwoopark7978/LVNet, 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.

exists Ran
ran, violated the contract we drafted
video-as-agent/videoagent/flowdiffusion/model/imagen.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

exists Ran
ran, violated the contract we drafted
video-as-agent/videoagent/flowdiffusion/goal_diffusion.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
first Ran
ran, violated the contract we drafted
video-as-agent/videoagent/flowdiffusion/model/imagen.py
code served (permissive licence) · get_code("3072294c9b32cf4b")
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 int, ndim 0, dtype family int, 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)

# The function `first` takes an array-like object and an optional default value
# It returns the first element of the array, or the default if the array is empty

# Test with a simple list
arr = [1, 2, 3, 4, 5]
d = None

ARGS = {
    "arr": arr,
    "d": d
}
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 int, ndim 0, dtype family int, 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
rearrange_dims Ran
ran, honoured the contract we drafted
video-as-agent/videoagent/flowdiffusion/model/resnet.py
code served (permissive licence) · get_code("a191f9f21d279753")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 1) 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 rearrange_dims takes a tensor and reshapes it based on its dimensionality
# It expects tensors with 2, 3, or 4 dimensions
# We'll create test cases for each valid dimension count

# Case 1: 2D tensor (batch_size=2, features=4)
tensor_2d = torch.randn(2, 4)

# Case 2: 3D tensor (batch_size=2, dim1=4, dim2=3)
tensor_3d = torch.randn(2, 4, 3)

# Case 3: 4D tensor (batch_size=2, dim1=4, dim2=3, dim3=5)
tensor_4d = torch.randn(2, 4, 3, 5)

# Test with 2D tensor as the primary case
ARGS = {
    "tensor": tensor_2d
}
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 3, dtype family float, shape (2, 4, 1) — shape (2, 4, 1) 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
tensors2vectors Ran
ran; our contract draft was wrong, not the code
video-as-agent/videoagent/flowdiffusion/goal_diffusion.py
code served (permissive licence) · get_code("f67b30f563b85481")
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; 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 numpy as np

torch.manual_seed(0)

# The function expects a list/iterable of tensors
# Each tensor is used in tensor2vector which:
# - calls permute(1, 2, 0) on it, so it needs shape (C, H, W)
# - converts to numpy and scales by (x - 0.5) * 1000
# - uses quiver plot on sliced data
# Let's create small tensors with shape (C, H, W) = (3, 8, 8) for RGB images

tensor1 = torch.rand(3, 8, 8)
tensor2 = torch.rand(3, 8, 8)

tensors = [tensor1, tensor2]

ARGS = {
    "tensors": tensors
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, 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 4, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:OSError)
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
upsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
video-as-agent/videoagent/flowdiffusion/model/resnet.py
code served (permissive licence) · get_code("31e7ed79c46ee9a9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 6, 10) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small input tensor [N, C, H, W]
hidden_states = torch.randn(2, 4, 3, 5)

# Create a simple kernel (1D that will be converted to 2D)
kernel = [1.0, 1.0]

# Upsampling factor
factor = 2

# Gain scaling factor
gain = 1.0

ARGS = {
    "hidden_states": hidden_states,
    "kernel": kernel,
    "factor": factor,
    "gain": gain,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 6, 10) — shape (2, 4, 6, 10) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
chat_with_openai Not yet run
unverified (harvested, no recorded run)
video-as-agent/videoagent/flowdiffusion/feedback_mw_extend.py
code served (permissive licence) · get_code("16845e6d52a74742")
How it ran

no invocation recorded.

chat_with_openai_rf Not yet run
unverified (harvested, no recorded run)
video-as-agent/videoagent/flowdiffusion/feedback_binary_rf.py
code served (permissive licence) · get_code("a78c6bc78ae4532c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 5 the same month, 7 later) and 4 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
exists 486 other papers
385 dated earlier, 11 the same month, 79 later, 9 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
exists 144 other papers
101 dated earlier, 4 the same month, 34 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
default 79 other papers
52 dated earlier, 3 the same month, 21 later, 3 same year, order not determinable · 15 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
and 76 more not named here
encode_image 76 other papers
31 dated earlier, 12 the same month, 32 later, 1 same year, order not determinable
2309.05950 (2023-09)
Language Models as Black-Box Optimizers for Vision-Language Models
2311.15732 (2023-11)
GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
2312.14867 (2023-12)
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
and 73 more not named here
identity 54 other papers
38 dated earlier, 2 the same month, 13 later, 1 same year, order not determinable · 11 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 51 more not named here
downsample_2d 7 other papers
6 dated earlier, 1 later
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
and 4 more not named here
upsample_2d 7 other papers
6 dated earlier, 1 later
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
and 4 more not named here
first 5 other papers
5 dated earlier
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2303.11916 (2023-03)
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
2308.08157 (2023-08)
Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis
and 2 more not named here
rearrange_dims 3 other papers
3 dated earlier
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
2310.08576 (2023-10)
Learning to Act from Actionless Videos through Dense Correspondences
tensors2vectors 1 other paper
1 dated earlier
2310.08576 (2023-10)
Learning to Act from Actionless Videos through Dense Correspondences

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

Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video plans which are then converted to robot controls to be executed. However, a major bottleneck in leveraging video generation for control lies in the quality of the generated videos, which often suffer from hallucinatory content and unrealistic physics, resulting in low task success when control actions are extracted from the generated videos. While scaling up dataset and model size provides a partial solution, integrating external feedback is both natural and essential for grounding video generation in the real world. With this observation, we propose VideoAgent for self-improving generated video plans based on external feedback. Instead of directly executing the generated video plan, VideoAgent first refines the generated video plans using a novel procedure which we call self-conditioning consistency, allowing inference-time compute to be turned into better generated video plans. As the refined video plan is being executed, VideoAgent can collect additional data from the environment to further improve video plan generation. Experiments in simulated robotic manipulation from MetaWorld and iTHOR show that VideoAgent drastically reduces hallucination, thereby boosting success rate of downstream manipulation tasks. We further illustrate that VideoAgent can effectively refine real-robot videos, providing an early indicator that robots can be an effective tool in grounding video generation in the physical world. Video demos and code can be found at https://video-as-agent.github.io.

For agents

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

get_harvested_code_for_paper("2410.10076")
get_code_for_paper("2410.10076")
have("2410.10076")

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

curl https://syntology.ai/api/ran/2410.10076.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.10076.svg)](https://syntology.ai/paper/2410.10076)

Connect an agent — have() is free.