SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.13552 · 2024

REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure of our instrument; 0 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/2411.13552.json · badge: /api/ran/2411.13552.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
microsoft/reducio-vae canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_best_aspect_ratio Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
microsoft/reducio-vae/scripts/extract_latent.py
code served (permissive licence) · get_code("bdef548c525ff7c6")
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 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.

from bisect import bisect_left

def get_best_aspect_ratio(aspect_ratio, n):
    """
    return the index of best available aspect ratio for videos
    """
    if n > aspect_ratio[-1]:
        return len(aspect_ratio) - 1
    elif n < aspect_ratio[0]:
        return 0
    else:
        pos = bisect_left(aspect_ratio, n)
        if aspect_ratio[pos] == n:
            return pos
        elif n > 1.0:
            return pos - 1
        else:
            return pos


ARGS = {
    "aspect_ratio": [0.5, 1.0, 1.5, 2.0, 2.5],
    "n": 1.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Commercial video generation models have exhibited realistic, high-fidelity results but are still restricted to limited access. One crucial obstacle for large-scale applications is the expensive training and inference cost. In this paper, we argue that videos contain significantly more redundant information than images, allowing them to be encoded with very few motion latents. Towards this goal, we design an image-conditioned VAE that projects videos into extremely compressed latent space and decode them based on content images. This magic Reducio charm enables 64x reduction of latents compared to a common 2D VAE, without sacrificing the quality. Building upon Reducio-VAE, we can train diffusion models for high-resolution video generation efficiently. Specifically, we adopt a two-stage generation paradigm, first generating a condition image via text-to-image generation, followed by text-image-to-video generation with the proposed Reducio-DiT. Extensive experiments show that our model achieves strong performance in evaluation. More importantly, our method significantly boosts the training and inference efficiency of video LDMs. Reducio-DiT is trained in just 3.2K A100 GPU hours in total and can generate a 16-frame 1024$\times$1024 video clip within 15.5 seconds on a single A100 GPU. Code released at https://github.com/microsoft/Reducio-VAE .

For agents

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

get_harvested_code_for_paper("2411.13552")
get_code_for_paper("2411.13552")
have("2411.13552")

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

curl https://syntology.ai/api/ran/2411.13552.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.13552.svg)](https://syntology.ai/paper/2411.13552)

Connect an agent — have() is free.