SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.10704 · 2020

Latent Video Transformer

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure 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/2006.10704.json · badge: /api/ran/2006.10704.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
rakhimovv/lvt canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran on a synthesized input
rakhimovv/lvt/vidgen/layers/all_gather.py
code served (permissive licence) · get_code("a89e04e4f41aac23")
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 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.distributed as dist
from unittest.mock import Mock, MagicMock, patch

torch.manual_seed(0)

# Mock distributed setup for CPU-only testing
class MockGroup:
    pass

mock_group = MockGroup()

# Patch torch.distributed to work without actual multi-process setup
with patch('torch.distributed.is_available', return_value=True):
    with patch('torch.distributed.is_initialized', return_value=False):
        # Create mock functions for distributed operations
        def mock_get_rank(group=None):
            return 0
        
        def mock_get_world_size(group=None):
            return 1
        
        def mock_all_gather(gather_list, tensor, group=None):
            gather_list[0].copy_(tensor)
            return None
        
        def mock_reduce(tensor, dst, op=None, group=None, async_op=False):
            mock_op = Mock()
            mock_op.wait = Mock()
            mock_op.is_completed = Mock(return_value=True)
            return mock_op
        
        # Patch the functions
        dist.get_rank = mock_get_rank
        dist.get_world_size = mock_get_world_size
        dist.all_gather = mock_all_gather
        dist.reduce = mock_reduce
        dist.group.WORLD = mock_group

# Create test tensors
tensor_input = torch.randn(2, 4)
gather_list = [torch.zeros(2, 4) for _ in range(1)]

# Create optional next_backprop module
next_backprop_module = nn.Linear(4, 4)

ARGS = {
    'gather_list': gather_list,
    'tensor': tensor_input,
    'group': mock_group,
    'next_backprop': next_backprop_module,
    'inplace': 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 list, ndim 3, 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
cat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rakhimovv/lvt/vidgen/layers/wrappers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xinyulyu/fgpl, is pointer only (licence: NONE) · get_code("6cbf46794989b731")
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 xinyulyu/fgpl, 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_out_channel Ran
ran on a synthesized input
rakhimovv/lvt/vidgen/layers/wrappers.py
code served (permissive licence) · get_code("cfb81a25ee5235c6")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a layer with out_channels attribute
class LayerWithOutChannels(nn.Module):
    def __init__(self):
        super().__init__()
        self.out_channels = 16

layer_with_out_channels = LayerWithOutChannels()

# Create a Conv2d layer (has out_channels attribute)
conv_layer = nn.Conv2d(3, 32, kernel_size=3)

# Create a Linear layer (has weight attribute)
linear_layer = nn.Linear(10, 20)

# Test with a layer that only has weight attribute
class LayerWithWeight(nn.Module):
    def __init__(self):
        super().__init__()
        self.weight = torch.randn(24, 10)

layer_with_weight = LayerWithWeight()

ARGS = {
    'layer': conv_layer
}
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
norm_layer Not yet run
unverified (harvested, no recorded run)
rakhimovv/lvt/vidgen/layers/wrappers.py
code served (permissive licence) · get_code("e50af06007f00579")
How it ran

no invocation recorded.

reduce_scatter Not yet run
unverified (harvested, no recorded run)
rakhimovv/lvt/vidgen/layers/all_gather.py
code served (permissive licence) · get_code("8261b186b6cd4b15")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
cat 18 other papers
5 dated earlier, 13 later · 3 only as an assembly brick
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
2002.10111 (2020-02)
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
and 15 more not named here

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

The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor Processing Units for parallel training. In this work, we address this problem via modeling the dynamics in a latent space. After the transformation of frames into the latent space, our model predicts latent representation for the next frames in an autoregressive manner. We demonstrate the performance of our approach on BAIR Robot Pushing and Kinetics-600 datasets. The approach tends to reduce requirements to 8 Graphical Processing Units for training the models while maintaining comparable generation quality.

For agents

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

get_harvested_code_for_paper("2006.10704")
get_code_for_paper("2006.10704")
have("2006.10704")

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

curl https://syntology.ai/api/ran/2006.10704.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.10704.svg)](https://syntology.ai/paper/2006.10704)

Connect an agent — have() is free.