Browse › Computer Vision › Image Generation › MNIST

Image Generation archive 2025-07-28

MNIST Benchmark (Image Generation)

15 rows 11 with code listed 6 metrics Dataset page

Syntology Since the archive (Syntology): none placed; 12 newer papers judged to report on this board so far.

Image Generation (synthesis) is the task of generating new images from an existing dataset.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

The archive carries no text for this table; the description above is the archive's text for the task Image Generation. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: FID (lower is better), Precision (higher is better), Recall (higher is better), PSNR (higher is better), SSIM (higher is better). Not inferred (points only, no best-so-far line): bits/dimension. Points are placed at the row's paper date, not an evaluation date; 12 of 15 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 Locally Masked PixelCNN (8 orders) 0.65 – Paper Code 2020 linked, not harvested report
2 Residual Flow 0.97 – Paper Code 2019 community repositories only · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified report
3 RNODE 0.97 – Paper Code 2020 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
4 MintNet 0.98 – Paper Code 2019 linked, not harvested report
5 i-ResNet 1.06 – Paper Code 2018 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified report
6 Sliced Iterative Generator 1.344.5 – Paper Code 2020 community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified report
7 PR-GLOW- Recall 4.450.770.72 – – – not matched report
8 GLF+perceptual loss (ours) 5.8 – Paper Code 2019 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified report
9 HypGAN 7.87 – Paper – 2021 no code linked report
10 JKO-iFlow 7.95 – – – not matched report
11 PR-GLOW- Precision 12.8840.8320.6509 – – – not matched report
12 Spiking-Diffusion 27.610.830.65 – Paper Code 2023 linked, not harvested report
13 Feature Alignment 37.50 – Paper Code 2021 linked, not harvested report
14 PresGAN 38.53 – Paper Code 2019 linked, not harvested report
15 Transition Matrix 17.940.697 – Paper Code 2024 linked, not harvested report

All 15 rows shown. 12 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 5 rows have a graph line, from 5 distinct papers. Rows whose paper has a sample that ran: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument). Papers: 5 with a sample that ran: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 5 rows with a graph line, 2 have an archive-official repository: on 0 a sample from it ran (0 with a run with no instrument failure), on 2 the samples that ran came from community repositories only, and on 0 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 41 samples: 35 ran (of which 1 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 18 where Syntology's instrument failed) · 6 unverified. Separately, 8 of those 41 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 37 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,581 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 12 proposed a result; of those 12, 8 gave no cell that passed the extractor's own checks, 4 were rejected by the independent check, 0 await a verdict and 0 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
Reflected Schrödinger Bridge Matching arXiv:2607.03626 3 Jul 2026 13 harvested: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified refused by a rule: the table reports a different split or setting than the leaderboard
PAPA: Online Personalized Active Preference Alignment arXiv:2607.00486 1 Jul 2026 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by rules: the model pointed at a header row; the model gave no value to check against the cell; the row label the model quoted is not the row's label
Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using... arXiv:2606.30310 29 Jun 2026 1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the model pointed at a header row
Implicit Neural Optimal Transport via Fixed-Point Optimization arXiv:2605.10792 11 May 2026 3 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified rejected by the independent check
DVD: Discrete Voxel Diffusion for 3D Generation and Editing arXiv:2605.07971 8 May 2026 13 harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified rejected by the independent check
Coupling Models for One-Step Discrete Generation arXiv:2605.07193 8 May 2026 11 harvested: 5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified rejected by the independent check
An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for... arXiv:2604.15171 16 Apr 2026 repository linked, no samples harvested refused by rules: the number the model quoted is not the number printed in the cell it pointed at; the row is an ablation variant, not the method itself
Infinite-dimensional generative diffusions via Doob's h-transform arXiv:2602.06621 6 Feb 2026 repository linked, no samples harvested rejected by the independent check
Approximating f-Divergences with Rank Statistics arXiv:2601.22784 30 Jan 2026 7 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified refused by rules: the model pointed at a header row; the number the model quoted is not the number printed in the cell it pointed at; the row label the model quoted is not the row's label
JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference arXiv:2512.22999 28 Dec 2025 11 harvested: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies arXiv:2509.19707 24 Sep 2025 2 harvested: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified refused by a rule: the model gave no value to check against the cell
Looking in the mirror: A faithful counterfactual explanation method for interpreting... arXiv:2509.16822 20 Sep 2025 repository linked, no samples harvested refused by a rule: several configurations of the method, and no metric direction to pick one

Syntology 12 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 8 counted above as giving no cell that passed the extractor's own checks are the 8 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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