Browse State-of-the-Art › Image Generation

Image Generation

3,102 papers with code · 93 benchmarks · 79 datasets archive 2025-07-28

Computer VisionMedicalMiscellaneousNatural Language Processing

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

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. p(y)
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. p(y|x).

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.

( Image credit: StyleGAN )

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

93 leaderboard tables shown for this task, 93 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 93 until expanded.

Syntology 54 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): ImageNet 256x256 (2 judged, 0 placed), CIFAR-10 (28 judged, 0 placed), FFHQ 256 x 256 (4 judged, 0 placed), CelebA 64x64 (9 judged, 0 placed), LSUN Bedroom 256 x 256 (6 judged, 1 placed), LSUN Churches 256 x 256 (2 judged, 1 placed), CelebA-HQ 256x256 (3 judged, 0 placed), CelebA 256x256 (1 judged, 0 placed), MNIST (12 judged, 0 placed), WISE (4 judged, 0 placed), FFHQ (4 judged, 0 placed), CelebA-HQ 1024x1024 (1 judged, 0 placed), AFHQ Cat (1 judged, 1 placed), AFHQV2 (1 judged, 0 placed), Fashion-MNIST (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ImageNet 256x256 (94 rows) SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG) Unified Continuous Generative Models code Syntology official (archive's flag): 19 ran · 19 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified Compare
CIFAR-10 (78 rows) GMem Generative Modeling with Explicit Memory code Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified Compare
ImageNet 64x64 (65 rows) SIMS Self-Improving Diffusion Models with Synthetic Data — — Compare
ImageNet 512x512 (52 rows) EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3) Direct Discriminative Optimization: Your Likelihood-Based Visual... code — Compare
FFHQ 256 x 256 (51 rows) StyleSAN-XL SAN: Inducing Metrizability of GAN with Discriminative Normalized... code Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified Compare
CelebA 64x64 (39 rows) DDPM-IP Input Perturbation Reduces Exposure Bias in Diffusion Models code Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
ImageNet 32x32 (35 rows) PaGoDA PaGoDA: Progressive Growing of a One-Step Generator from a... code Syntology official (archive's flag): 15 ran · 15 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 2 unverified Compare
LSUN Bedroom 256 x 256 (32 rows) Diffusion ProjectedGAN Diffusion-GAN: Training GANs with Diffusion code Syntology community repositories only · 15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified Compare
STL-10 (31 rows) Diffusion ProjectedGAN Diffusion-GAN: Training GANs with Diffusion code Syntology community repositories only · 15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified Compare
LSUN Churches 256 x 256 (27 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
ImageNet 128x128 (23 rows) SiD2 Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion — — Compare
FFHQ 1024 x 1024 (20 rows) StyleSAN-XL SAN: Inducing Metrizability of GAN with Discriminative Normalized... code Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified Compare
CelebA-HQ 256x256 (19 rows) RDM Relay Diffusion: Unifying diffusion process across resolutions for... code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified Compare
CelebA 256x256 (17 rows) Efficient-VDVAE Efficient-VDVAE: Less is more code — Compare
MNIST (15 rows) Locally Masked PixelCNN (8 orders) Locally Masked Convolution for Autoregressive Models code — Compare
WISE (14 rows) MindOmni (w/ cot) MindOmni: Unleashing Reasoning Generation in Vision Language... code — Compare
FFHQ-U (13 rows) Alias-Free-R Alias-Free Generative Adversarial Networks code Syntology official (archive's flag): 3 ran · 30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 4 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
FFHQ (12 rows) Anycost GAN Anycost GANs for Interactive Image Synthesis and Editing code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
Binarized MNIST (10 rows) CR-NVAE Consistency Regularization for Variational Auto-Encoders code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 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) · 1 unverified Compare
CelebA-HQ 1024x1024 (10 rows) StyleSwin StyleSwin: Transformer-based GAN for High-resolution Image Generation code Syntology official (archive's flag): 2 ran · 5 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; 5 where Syntology's instrument failed) · 0 unverified Compare
CIFAR-100 (9 rows) LeCAM (StyleGAN2 + ADA) Regularizing Generative Adversarial Networks under Limited Data code Syntology official (archive's flag): 3 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
AFHQ Cat (8 rows) Vision-aided GAN Ensembling Off-the-shelf Models for GAN Training code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
LSUN Cat 256 x 256 (8 rows) Vision-aided GAN Ensembling Off-the-shelf Models for GAN Training code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
AFHQV2 (7 rows) Polarity-StyleGAN3 Polarity Sampling: Quality and Diversity Control of Pre-Trained... code — Compare
CelebA-HQ 128x128 (7 rows) U-Net GAN A U-Net Based Discriminator for Generative Adversarial Networks code — Compare
Fashion-MNIST (7 rows) GLF+perceptual loss (ours) Generative Latent Flow code Syntology 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 Compare
TextAtlasEval (7 rows) Grok3 — — — Compare
AFHQ Dog (6 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
Cityscapes (6 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
CLEVR (6 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
LSUN Horse 256 x 256 (6 rows) Vision-aided GAN Ensembling Off-the-shelf Models for GAN Training code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
AFHQ Wild (5 rows) Vision-aided GAN Ensembling Off-the-shelf Models for GAN Training code Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
CelebA 128x128 (5 rows) U-Net GAN A U-Net Based Discriminator for Generative Adversarial Networks code — Compare
Places50 (5 rows) SinDiffusion SinDiffusion: Learning a Diffusion Model from a Single Natural Image code Syntology official (archive's flag): 17 ran · 17 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified Compare
ARKitScenes (4 rows) GAUDI GAUDI: A Neural Architect for Immersive 3D Scene Generation code — Compare
CUB 128 x 128 (4 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
Pokemon 256x256 (4 rows) StyleGAN-XL StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets code Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified Compare
Replica (4 rows) GAUDI GAUDI: A Neural Architect for Immersive 3D Scene Generation code — Compare
Stanford Cars (4 rows) Projected GANs Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
Stanford Dogs (4 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
VizDoom (4 rows) GAUDI GAUDI: A Neural Architect for Immersive 3D Scene Generation code — Compare
VLN-CE (4 rows) GAUDI GAUDI: A Neural Architect for Immersive 3D Scene Generation code — Compare
ADE-Indoor (3 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
CAT 256x256 (3 rows) StyleGAN2 + DA + RLC (Ours) Regularizing Generative Adversarial Networks under Limited Data code Syntology official (archive's flag): 3 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
CelebA-HQ 64x64 (3 rows) COCO-GAN COCO-GAN: Generation by Parts via Conditional Coordinating code Syntology 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) · 5 unverified Compare
CIFAR-10 (10% data) (3 rows) DiffAugment-StyleGAN2 Differentiable Augmentation for Data-Efficient GAN Training code Syntology official (archive's flag): 7 ran · 49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified Compare
CIFAR-10 (20% data) (3 rows) DiffAugment-StyleGAN2 Differentiable Augmentation for Data-Efficient GAN Training code Syntology official (archive's flag): 7 ran · 49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified Compare
FFHQ 128 x 128 (3 rows) DDPM-IP Input Perturbation Reduces Exposure Bias in Diffusion Models code Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
FFHQ 512 x 512 (3 rows) StyleSAN-XL SAN: Inducing Metrizability of GAN with Discriminative Normalized... code Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified Compare
LSUN Bedroom (3 rows) StyleGAN A Style-Based Generator Architecture for Generative Adversarial Networks code Syntology official (archive's flag): 1 ran · 244 ran (of which 147 constructed an object rather than computing a result; 217 with no instrument failure: 17 honoured, 3 violated, 197 with no contract checked; 27 where Syntology's instrument failed) · 152 unverified Compare
LSUN Bedroom 64 x 64 (3 rows) WGAN-GP + TTUR + Alex-Adam Fundamental Benefit of Alternating Updates in Minimax Optimization code Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result Compare
MetFaces (3 rows) t-Stylegan3-ada (NVIDIA pre-trained) Signature and Log-signature for the Study of Empirical... code — Compare
MetFaces-U (3 rows) Alias-Free-R Alias-Free Generative Adversarial Networks code Syntology official (archive's flag): 3 ran · 30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 4 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified Compare
ObjectsRoom (3 rows) GENESIS-V2 GENESIS-V2: Inferring Unordered Object Representations without... code — Compare
Pokemon 1024x1024 (3 rows) StyleGAN-XL StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets code Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified Compare
ShapeStacks (3 rows) GENESIS-V2 GENESIS-V2: Inferring Unordered Object Representations without... code — Compare
Stacked MNIST (3 rows) VAEBM VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models code Syntology official (archive's flag): 5 ran · 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
TiO_2 nanoparticle (3 rows) F-ANcGAN F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative... code — Compare
AFHQ-v2 64x64 (2 rows) SiDA-EDM Adversarial Score identity Distillation: Rapidly Surpassing the... code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
FFHQ 64x64 (2 rows) SiDA-EDM Adversarial Score identity Distillation: Rapidly Surpassing the... code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
iNaturalist 2019 (2 rows) StyeGAN2 + NoisyTwins NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs code — Compare
LSUN Bedroom 128 x 128 (2 rows) LadaGAN Efficient generative adversarial networks using linear... code — Compare
LSUN Car 512 x 384 (2 rows) Polarity-StyleGAN2 Polarity Sampling: Quality and Diversity Control of Pre-Trained... code — Compare
Oxford 102 Flowers 256 x 256 (2 rows) Projected GAN Projected GANs Converge Faster code Syntology official (archive's flag): 12 ran · 38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified Compare
RC-49 (2 rows) cDR-RS Efficient Subsampling of Realistic Images From GANs Conditional on... code — Compare
1,078 People 3D Faces Collection Data (1 row) Sessiz çığlık 0-Hecke modules for row-strict dual immaculate functions — — Compare
25% ImageNet 128x128 (1 row) LeCAM + DA Regularizing Generative Adversarial Networks under Limited Data code Syntology official (archive's flag): 3 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
‘ไอซ์ ปรีชญา’ ลืมปิดไลฟ์สดตอนอาบน้ำ คลิปถูกคนดีแชร์ออนไลน์ (1 row) as Image Generation From Small Datasets via Batch Statistics Adaptation code Syntology official (archive's flag): 4 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
CelebA (1 row) FInCFlow FInC Flow: Fast and Invertible k ×k Convolutions for Normalizing Flows — — Compare
CelebA-HQ (1 row) DDPM Normalizing Flow-Based Metric for Image Generation code — Compare
CelebA-HQ 512x512 (1 row) WaveDiff Wavelet Diffusion Models are fast and scalable Image Generators code — Compare
Cityscapes-25K 256x512 (1 row) SB-GAN Semantic Bottleneck Scene Generation code — Compare
Cityscapes-5K 256x512 (1 row) SB-GAN Semantic Bottleneck Scene Generation code — Compare
EMNIST-Letters (1 row) Spiking-Diffusion Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with... code — Compare
FFHQ 64x64 - 4x upscaling (1 row) PFGM++ PFGM++: Unlocking the Potential of Physics-Inspired Generative Models code Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
GQN (1 row) GENESIS GENESIS: Generative Scene Inference and Sampling with... code — Compare
ImageNet 256x256 - 1 labeled data per class (1 row) DPT — — — Compare
ImageNet 256x256 - 1% labeled data (1 row) DPT — — — Compare
ImageNet 256x256 - 2 labeled data per class (1 row) DPT — — — Compare
ImageNet 256x256 - 5 labeled data per class (1 row) DPT — — — Compare
Indian Celebs 256 x 256 (1 row) MSG-StyleGAN MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks code Syntology community repositories only · 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
KMNIST (1 row) Spiking-Diffusion Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with... code — Compare
Landscapes 256 x 256 (1 row) CIPS Image Generators with Conditionally-Independent Pixel Synthesis code — Compare
LLVIP (1 row) pix2pix LLVIP: A Visible-infrared Paired Dataset for Low-light Vision code — Compare
LSUN (1 row) BigGAN + gSR Improving GANs for Long-Tailed Data through Group Spectral Regularization code Syntology official: harvested, nothing ran · 0 ran · 3 unverified Compare
LSUN Car 256 x 256 (1 row) StyleGAN2 Analyzing and Improving the Image Quality of StyleGAN code Syntology official: harvested, nothing ran · 68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified Compare
LSUN tower 64x64 (1 row) DDPM-IP Input Perturbation Reduces Exposure Bias in Diffusion Models code Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Multi-dSprites (1 row) GENESIS GENESIS: Generative Scene Inference and Sampling with... code — Compare
NASA Perseverance (1 row) Stylegan2-ada Signature and Log-signature for the Study of Empirical... code — Compare
Oxford 102 Flowers 128x128 (1 row) QSNGAN Quaternion Generative Adversarial Networks code — Compare
Satellite-Buildings 256 x 256 (1 row) CIPS Image Generators with Conditionally-Independent Pixel Synthesis code — Compare
Satellite-Landscapes 256 x 256 (1 row) CIPS Image Generators with Conditionally-Independent Pixel Synthesis code — Compare
SDSS Galaxies (1 row) AstroDDPM Realistic galaxy image simulation via score-based generative models code Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line 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”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

79 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 79 until expanded.

Subtasks archive 2025-07-28

23 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 6,689 · with a code link: 3,102 · where Syntology ran a sample: 1,223 (1,036 with a run with no instrument failure, 187 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1,223 of 6,689 tagged: 1,036 with a run with no instrument failure, 187 where every run was a failure of Syntology's instrument)

Page 1 of 67: papers 1 to 100 of 6,689, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line 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”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 93 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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