Papers › Flow++: Improving Flow-Based Generative Models with Variational Dequantization and...

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

1 Feb 2019ICLR 2019 5arXiv:1902.00275archive 2025-07-28

Jonathan Ho, Xi Chen, Aravind Srinivas, Yan Duan, Pieter Abbeel

Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to state-of-the-art autoregressive models. In this paper, we investigate and improve upon three limiting design choices employed by flow-based models in prior work: the use of uniform noise for dequantization, the use of inexpressive affine flows, and the use of purely convolutional conditioning networks in coupling layers. Based on our findings, we propose Flow++, a new flow-based model that is now the state-of-the-art non-autoregressive model for unconditional density estimation on standard image benchmarks. Our work has begun to close the significant performance gap that has so far existed between autoregressive models and flow-based models. Our implementation is available at https://github.com/aravindsrinivas/flowpp

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1902.00275")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: official repository: 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

aravind0706/flowpp officialmentioned in papermentioned on GitHubtfMIT report
aravindsrinivas/flowpp officialmentioned in papermentioned on GitHubtfMIT report
SamArgt/AudioSourceSep mentioned on GitHubtf report
hojonathanho/localbitsback mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from aravind0706/flowpp. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

assert_in_range aravind0706/flowpp/flows_imagenet/logistic.py official repository unverified MIT (permissive) · 65754dd997703c12 · report
at_least_float32 aravind0706/flowpp/flows_imagenet/launchers/imagenet32_official.py official repository unverified MIT (permissive) · 5f0f74ae9d431c1c · report
conv2d aravind0706/flowpp/flows/flows.py official repository unverified MIT (permissive) · 9df274ab304130e2 · report
dense aravind0706/flowpp/flows/flows.py official repository unverified MIT (permissive) · 7c31d5dfdb4e6308 · report
get_var aravind0706/flowpp/flows_imagenet/launchers/imagenet32_official.py official repository unverified MIT (permissive) · 952f606576c632c7 · report
get_var aravind0706/flowpp/flows/flows.py official repository unverified MIT (permissive) · 9d6d831a4e81b501 · report
tile_imgs aravind0706/flowpp/flows_imagenet/utils.py official repository unverified MIT (permissive) · f7bc5864104e41ee · report
tile_imgs aravind0706/flowpp/flows/utils.py official repository unverified MIT (permissive) · 77ffd1982c6a4f9a · report
to_default_floatx aravind0706/flowpp/flows_imagenet/launchers/imagenet32_official.py official repository unverified MIT (permissive) · 60187f793be7f93d · report

Tasks

Computational EfficiencyDensity EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 32x32 Flow++ bpd 3.86 #27 of 35 Archive leaderboard report
Image Generation ImageNet 64x64 Flow++ Bits per dim 3.69 #52 of 65 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections