Papers › Bellman Optimal Stepsize Straightening of Flow-Matching Models

Bellman Optimal Stepsize Straightening of Flow-Matching Models

27 Dec 2023arXiv:2312.16414archive 2025-07-28

Bao Nguyen, Binh Nguyen, Viet Anh Nguyen

Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Stepsize Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programming algorithm that optimizes the stepsizes of the pretrained network. Then, it refines the velocity network to match the optimal step sizes, aiming to straighten the generation paths. Extensive experimental evaluations across image generation tasks demonstrate the efficacy of BOSS in terms of both resource utilization and image quality. Our results reveal that BOSS achieves substantial gains in efficiency while maintaining competitive sample quality, effectively bridging the gap between low-resource constraints and the demanding requirements of flow-matching generative models. Our paper also fortifies the responsible development of artificial intelligence, offering a more sustainable generative model that reduces computational costs and environmental footprints. Our code can be found at https://github.com/nguyenngocbaocmt02/BOSS.

PaperPDFCodeCode 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="2312.16414")

Code

Syntology Ran 8 of 14 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nguyenngocbaocmt02/boss officialmentioned in papermentioned on GitHubjax 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

14 samples harvested; 8 ran; 0 honoured the contract we drafted; 6 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.

4ran · our draft was wrong
4ran
6unverified

Licence: 14 of the 14 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 nguyenngocbaocmt02/boss. “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.

format_time nguyenngocbaocmt02/boss/ImageGeneration/dnnlib/util.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 674eca7b9e1b6439 · report
format_time_brief nguyenngocbaocmt02/boss/ImageGeneration/dnnlib/util.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 32af001972a0699f · report
get_data_inverse_scaler nguyenngocbaocmt02/boss/ImageGeneration/datasets.py official repository ran · our draft was wrong no licence file found · pointer only · 6c419026e778dee2 · report
get_data_scaler nguyenngocbaocmt02/boss/ImageGeneration/datasets.py official repository ran · our draft was wrong no licence file found · pointer only · 346d2e6cc8b48a5d · report
get_dataset_stats nguyenngocbaocmt02/boss/ImageGeneration/evaluation.py official repository ran no licence file found · pointer only · e65d7c2e1dad4e1e · report
get_optimizer nguyenngocbaocmt02/boss/ImageGeneration/losses.py official repository ran no licence file found · pointer only · 8ff7c24dade9904c · report
optimization_manager nguyenngocbaocmt02/boss/ImageGeneration/losses.py official repository ran no licence file found · pointer only · 366bb8c7035a2fc8 · report
variance_scaling nguyenngocbaocmt02/boss/ImageGeneration/models/layers.py official repository ran no licence file found · pointer only · 3ac11bfe0ae80195 · report
ask_yes_no nguyenngocbaocmt02/boss/ImageGeneration/dnnlib/util.py official repository unverified no licence file found · pointer only · 9d31d2c4cd16bb2d · report
classifier_fn_from_tfhub nguyenngocbaocmt02/boss/ImageGeneration/evaluation.py official repository unverified no licence file found · pointer only · 54a00db9aadf092f · report
crop_resize nguyenngocbaocmt02/boss/ImageGeneration/datasets.py official repository unverified no licence file found · pointer only · fd14d238ccd5f679 · report
get_act nguyenngocbaocmt02/boss/ImageGeneration/models/layers.py official repository unverified no licence file found · pointer only · db5f935a1d6b4c2c · report
get_div_fn nguyenngocbaocmt02/boss/ImageGeneration/likelihood.py official repository unverified no licence file found · pointer only · 0bfcb6b2d940e393 · report
ncsn_conv1x1 nguyenngocbaocmt02/boss/ImageGeneration/models/layers.py official repository unverified no licence file found · pointer only · 85b2235eb7afaa4f · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation AFHQ Cat BOSS clean-FID 22.2 #3 of 8 Archive leaderboard report
Image Generation CelebA-HQ 256x256 BOSS clean-FID 20.13 #19 of 19 Archive leaderboard report
Image Generation LSUN Bedroom BOSS clean-FID 12.13 #3 of 3 Archive leaderboard report
Image Generation LSUN Churches 256 x 256 BOSS clean-FID 13.21 #27 of 27 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