SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.10258 · ICLR · 2021

Hierarchical Autoregressive Modeling for Neural Video Compression

Stephan Mandt, Yibo Yang, Ruihan Yang, Joseph Marino

arXiv · PDF · Open in the Atlas

Code that ran

24 of 29 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (10 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 20 have no contract verdict; 2 failures of our instrument; 5 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/2010.10258.json · badge: /api/ran/2010.10258.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
buggyyang/hier-video-compression canonical (classifier label)
classifier basis: classifier_2025
16 ran · 5 no recorded run
buggyyang/youtube-nt canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
BaseDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("2efaa759079d076c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

BaseEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("25e59bb3d170a01f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

Coder Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("f3cdfc0b37e6a8e6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

FlexiblePrior Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("fe8f871c8165f89c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

GDN Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("83233d52a69b71da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

GDN1 Ran
ran on a synthesized input
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("0329cd658af6bfaa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

HyperDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("28fdc241caf365cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

HyperEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("fcb0a33f9a2bf52a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

LowerBound Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("12677b56c4c6cf41")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

NormalDistribution Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("129bfe8ee13e3894")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

PriorFunction Ran
ran on a synthesized input
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("2c9d25e2d787e008")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

STERound Ran
ran on a synthesized input · constructed an object; no result was computed
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("3c172097e4c4b967")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

compute_downscale_factor Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/video_manager.py
code served (permissive licence) · get_code("880266a6c627174a")
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 numpy as np

# Analyze the function: it takes frame_width as input
# and returns an int based on DEFAULT_DOWNSCALE_FACTORS lookup

ARGS = {
    "frame_width": 1920
}
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 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
get_and_create_path Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/platform.py
code served (permissive licence) · get_code("bb7f82c4f26327cf")
How it ran

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

import os.path
import tempfile

ARGS = {
    "file_path": "output.txt",
    "output_directory": tempfile.gettempdir()
}
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 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_csv_reader Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/platform.py
code served (permissive licence) · get_code("8b4179145570dad9")
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 reader. 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 csv
from io import StringIO

# Create a StringIO object to act as a file handle with CSV content
csv_content = "name,age,city\nAlice,30,NYC\nBob,25,LA\n"
file_handle = StringIO(csv_content)

ARGS = {
    "file_handle": file_handle
}
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 reader — a reader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a reader 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_csv_writer Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/platform.py
code served (permissive licence) · get_code("1a3e221bd9a9f50e")
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 writer. 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 csv
import io

# Create a file handle (StringIO for in-memory file)
file_handle = io.StringIO()

ARGS = {
    "file_handle": file_handle
}
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 writer — a writer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a writer 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_num_frames Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/video_manager.py
code served (permissive licence) · get_code("e60be8fb7c5db5ea")
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 math
import cv2


class MockVideoCapture:
    """Mock cv2.VideoCapture that returns frame counts"""
    def __init__(self, frame_count):
        self.frame_count = frame_count
    
    def get(self, prop_id):
        if prop_id == cv2.CAP_PROP_FRAME_COUNT:
            return float(self.frame_count)
        return 0.0


cap_list = [
    MockVideoCapture(100),
    MockVideoCapture(250),
    MockVideoCapture(75)
]

ARGS = {
    "cap_list": cap_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2 — 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
get_plural Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/cli/context.py
code served (permissive licence) · get_code("5582430f30b1e688")
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

torch.manual_seed(0)

# The function get_plural takes a single parameter val_list and checks its length
# It returns 's' if len(val_list) > 1, otherwise returns ''
# We need to provide a list as the argument

# Test case 1: List with more than one element (should return 's')
val_list_multiple = [1, 2, 3]

ARGS = {
    'val_list': val_list_multiple
}
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 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_scenes_from_cuts Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/scene_manager.py
code served (permissive licence) · get_code("fcb377955a0b8932")
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.

class FrameTimecode:
    """Minimal FrameTimecode class for testing."""
    def __init__(self, timecode=0, fps=30):
        self.frame_num = timecode if isinstance(timecode, int) else 0
        self.fps = fps
    
    def __add__(self, other):
        if isinstance(other, int):
            return FrameTimecode(self.frame_num + other, self.fps)
        elif isinstance(other, FrameTimecode):
            return FrameTimecode(self.frame_num + other.frame_num, self.fps)
        return NotImplemented
    
    def __radd__(self, other):
        return self.__add__(other)
    
    def __repr__(self):
        return f"FrameTimecode({self.frame_num}, fps={self.fps})"
    
    def __eq__(self, other):
        if isinstance(other, FrameTimecode):
            return self.frame_num == other.frame_num
        return False


base_timecode = FrameTimecode(0, fps=30)
cut_list = [
    FrameTimecode(100, fps=30),
    FrameTimecode(250, fps=30),
    FrameTimecode(400, fps=30),
]
num_frames = 500
start_frame = 0

ARGS = {
    "cut_list": cut_list,
    "base_timecode": base_timecode,
    "num_frames": num_frames,
    "start_frame": start_frame,
}
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 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
get_video_name Ran
ran on a synthesized input
buggyyang/youtube-nt/PySceneDetect/scenedetect/video_manager.py
code served (permissive licence) · get_code("16368e5d19486e5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family 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

# The function get_video_name takes one parameter: video_file
# It can be either:
# 1. An integer representing a device ID
# 2. A string representing a file path

# Test case 1: integer device ID
video_file_int = 42

# Test case 2: file path string
video_file_path = "/path/to/video/sample_video.mp4"

# We'll use the integer case for ARGS
ARGS = {
    'video_file': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
noise Ran
ran; our contract draft was wrong, not the code
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("5499218583ec12e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

quantize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("771654b864892612")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

round_w_offset Ran
ran, honoured the contract we drafted
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("621a39b9552a568f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

universal_quantize Ran
ran, honoured the contract we drafted
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("491474fe9b136c86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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.

CondModel Not yet run
unverified (harvested, no recorded run)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("a63896ce6119a75a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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. No invocation recorded.

CustomSequential Not yet run
unverified (harvested, no recorded run)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("50f309ba206df2c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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. No invocation recorded.

HyperCondDecoder Not yet run
unverified (harvested, no recorded run)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("735e60ddbd1ad8fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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. No invocation recorded.

SimpleModel Not yet run
unverified (harvested, no recorded run)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("de507745c7134871")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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. No invocation recorded.

VBRCondition Not yet run
unverified (harvested, no recorded run)
buggyyang/hier-video-compression/models.py
pointer only (licence: NONE) · get_code("143d83707982d3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buggyyang/hier-video-compression 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. No invocation recorded.

Also present in other papers' code

Of 29 samples lifted from this paper's linked repositories, 29 carry a function identity and 0 do not. Of the 29 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 28 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
LowerBound
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2109.15047 (2021-09)
Deep Contextual Video Compression
2302.05071 (2023-02)
EVC: Towards Real-Time Neural Image Compression with Mask Decay

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

showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autoregressive generative models and the task of lossy video compression. Specifically, we view recent neural video compression methods (Lu et al., 2019; Yang et al., 2020b;Agustsson et al., 2020) as instances of a generalized stochastic temporal autoregressive transform, and propose avenues for enhancement based on this insight. Comprehensive evaluations on large-scale video data show improved rate-distortion performance over both state-of-the-art neural and conventional video compression methods 1 .

For agents

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

get_harvested_code_for_paper("2010.10258")
get_code_for_paper("2010.10258")
have("2010.10258")

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

curl https://syntology.ai/api/ran/2010.10258.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.10258.svg)](https://syntology.ai/paper/2010.10258)

Connect an agent — have() is free.