SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.13202 · ICML · 2021

Simple and Effective VAE Training with Calibrated Decoders

Sergey Levine, Oleh Rybkin, Kostas Daniilidis

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 failures of our instrument; 1 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/2006.13202.json · badge: /api/ran/2006.13202.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
orybkin/sigma-vae-pytorch canonical (classifier label)
classifier basis: classifier_2025
6 ran · 1 no recorded run
FunctionStatusWhere it lives
Flatten Ran
ran on a synthesized input
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("b48f592cc5b0f4c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

UnFlatten Ran
ran on a synthesized input · constructed an object; no result was computed
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("0097f92921cb5c04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

gaussian_nll Ran
ran; our contract draft was wrong, not the code
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("85038890e349231c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

gaussian_nll Ran
ran, honoured the contract we drafted
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("b67c41c224081421")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

softclip Ran
ran; our contract draft was wrong, not the code
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("afbe2793658279b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

softclip Ran
ran; our contract draft was wrong, not the code
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("ede71767cb8a75e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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.

ConvVAE Not yet run
unverified (harvested, no recorded run)
orybkin/sigma-vae-pytorch/model.py
pointer only (licence: NONE) · get_code("0fa76b9a6fc9475e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, orybkin/sigma-vae-pytorch 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
Flatten
brick of this paper's assembly: helper
6 other papers
3 dated earlier, 3 later · 4 only as an assembly brick
1705.05363 (2017-05)
Curiosity-driven Exploration by Self-supervised Prediction
1810.12894 (2018-10)
Exploration by Random Network Distillation
2002.10025 (2020-02)
Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference
and 3 more not named here
gaussian_nll
brick of this paper's assembly: loss
1 other paper
1 later
2007.02443 (2020-07)
Pseudo-Rehearsal for Continual Learning with Normalizing Flows

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

Variational autoencoders (VAEs) provide an effective and simple method for modeling complex distributions. However, training VAEs often requires considerable hyperparameter tuning to determine the optimal amount of information retained by the latent variable. We study the impact of calibrated decoders, which learn the uncertainty of the decoding distribution and can determine this amount of information automatically, on the VAE performance. While many methods for learning calibrated decoders have been proposed, many of the recent papers that employ VAEs rely on heuristic hyperparameters and ad-hoc modifications instead. We perform the first comprehensive comparative analysis of calibrated decoder and provide recommendations for simple and effective VAE training. Our analysis covers a range of image and video datasets and several single-image and sequential VAE models. We further propose a simple but novel modification to the commonly used Gaussian decoder, which computes the prediction variance analytically. We observe empirically that using heuristic modifications is not necessary with our method. Project website: https: //orybkin.github.io/sigma-vae/.

For agents

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

get_harvested_code_for_paper("2006.13202")
get_code_for_paper("2006.13202")
have("2006.13202")

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

curl https://syntology.ai/api/ran/2006.13202.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.13202.svg)](https://syntology.ai/paper/2006.13202)

Connect an agent — have() is free.