Home › Code › patchify

patchify

Syntologyentry name in harvested coderead from the graph 2026-09-24

patchify appears in the code Syntology harvested for 32 papers, as 25 distinct code bodies found in 36 places (a place is one code body under one paper). At least one of them ran in 20 of the papers; 7 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named patchify do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 13 of the 25 distinct code bodies named patchify; 12 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
7ran · fixture could not drive it
5ran
12unverified
7fingerprinted

Licence is a property of each copy, so it is counted per place: 15 of the 36 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

32 papers shown of 32, newest first; 36 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images added by Syntology 2025-11 (from id) AIDC-AI/Omni-View/modeling/bagel/bagel.py 06c91d3233a2f559 ran · fixture could not drive it fingerprinted Apache-2.0 (permissive)
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback added by Syntology 2025-11 (from id) alibaba-damo-academy/Lumos-Custom/UniLumos/UniLumos/src/schedulers/rectified_flow.py 18f75e876d5831d4 ran · fixture could not drive it no licence file found · pointer only
DRAG: Data Reconstruction Attack using Guided Diffusion added by Syntology 2025-09 (from id) ntuaislab/DRAG/models/distance.py 48f66cfa3b0fd70d unverified licence not identified · pointer only
arXiv:2507.17312 2025-07 (from id) pq-chen/CasP/src/models/nets/casp/utils.py 9487332eba3f7014 unverified Apache-2.0 (permissive)
Omni-Video: Democratizing Unified Video Understanding and Generation 8 Jul 2025 sais-fuxi/omni-video/omnivideo/modules/vae2_2.py d12b826fb528dd75 unverified no licence file found · pointer only
arXiv:2506.03110 2025-06 (from id) shuaiyi308/ReCIT/methods/visiontransformer.py 516cbd03fb9c9dbd ran · fixture could not drive it no licence file found · pointer only
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention 23 May 2025 DreamTechAI/Direct3D-S2/direct3d_s2/modules/spatial.py e6b8cd9f318cc00b unverified MIT (permissive)
AdaWorld: Learning Adaptable World Models with Latent Actions 24 Mar 2025 little-podi/adaworld/lam/lam/modules/lam.py 039179bb223e6c09 ran · fixture could not drive it fingerprinted Apache-2.0 (permissive)
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation 25 Feb 2025 microsoft/art-msra/multi_layer_gen/custom_model_transp_vae.py 91a80a2215fe15e4 unverified MIT (permissive)
LTX-Video: Realtime Video Latent Diffusion 30 Dec 2024 Lightricks/LTX-Video/ltx_video/models/autoencoders/causal_video_autoencoder.py b66d92e3db33734e unverified Apache-2.0 (permissive)
LTX-Video: Realtime Video Latent Diffusion 30 Dec 2024 Lightricks/LTX-Video/ltx_video/models/autoencoders/video_autoencoder.py 79dc833d8e0d8a46 unverified Apache-2.0 (permissive)
Structured 3D Latents for Scalable and Versatile 3D Generation 2 Dec 2024 Microsoft/TRELLIS/trellis/modules/spatial.py e6b8cd9f318cc00b unverified MIT (permissive)
PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics 15 Sep 2024 felix-lyx/prose/prose_fd/models/embedder.py 7e71d4e3b4f9a5e1 ran MIT (permissive)
Deep Patch Visual SLAM 3 Aug 2024 princeton-vl/dpvo/dpvo/utils.py 7e9ef04c656a01f5 ran fingerprinted MIT (permissive)
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models 20 Jun 2024 stylebreeder/stylebreeder-code/utils.py 5db42d2262ce7bb3 ran fingerprinted MIT (permissive)
TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting 23 Apr 2024 Fictionarry/TalkingGaussian/utils/loss_utils.py f757e041d69bb770 unverified no licence file found · pointer only
On Pretraining Data Diversity for Self-Supervised Learning 20 Mar 2024 hammoudhasan/diversityssl/solo/losses/mae.py 3e6a557bf1ad83d9 ran MIT (permissive)
Non-negative Contrastive Learning 19 Mar 2024 PKU-ML/non_neg/solo/losses/mae.py 3e6a557bf1ad83d9 ran no licence file found · pointer only
Do Generated Data Always Help Contrastive Learning? 19 Mar 2024 PKU-ML/adainf/solo-learn/solo/losses/mae.py 3e6a557bf1ad83d9 ran no licence file found · pointer only
Scalable Diffusion Models with State Space Backbone 8 Feb 2024 feizc/dis/models_dis.py 9cf076a2ae913f94 ran · fixture could not drive it fingerprinted no licence file found · pointer only
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation 31 Jan 2024 ymy-k/hi-sam/demo_hisam.py 68c887d10fe2881b ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection 20 Oct 2023 identical code first harvested elsewhere 7a7de2a8e080f047 ran · fixture could not drive it fingerprinted licence of this copy not recorded
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection 20 Oct 2023 identical code first harvested elsewhere 9cf076a2ae913f94 ran · fixture could not drive it fingerprinted licence of this copy not recorded
FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning 4 Oct 2023 ofskean/frossl/solo/losses/mae.py 3e6a557bf1ad83d9 ran no licence file found · pointer only
Mechanism of feature learning in convolutional neural networks 1 Sep 2023 aradha/convrfm/cnfa_verification/pretrained_conv_nfa.py e0c0dc70dcaf23d7 unverified no licence file found · pointer only
How Much Temporal Long-Term Context is Needed for Action Segmentation? 22 Aug 2023 ltcontext/ltcontext/ltc/model/attention_utils.py 89736b7f0b2556b1 ran licence not identified · pointer only
Masked Diffusion Models Are Fast Distribution Learners 20 Jun 2023 jiachenlei/maskdm/models/mask_uvit.py 9cf076a2ae913f94 ran · fixture could not drive it fingerprinted MIT (permissive)
Fast Training of Diffusion Models with Masked Transformers 15 Jun 2023 anima-lab/maskdit/train_utils/loss.py e37dd1efa8f2e9bd unverified MIT (permissive)
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels 21 Feb 2023 identical code first harvested elsewhere 7a7de2a8e080f047 ran · fixture could not drive it fingerprinted licence of this copy not recorded
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels 21 Feb 2023 baofff/u-vit/libs/uvit.py 9cf076a2ae913f94 ran · fixture could not drive it fingerprinted MIT (permissive)
All are Worth Words: A ViT Backbone for Diffusion Models 25 Sep 2022 identical code first harvested elsewhere 9cf076a2ae913f94 ran · fixture could not drive it fingerprinted licence of this copy not recorded
ConvMAE: Masked Convolution Meets Masked Autoencoders 8 May 2022 mx-mark/dmjd/util/hog_tensor.py f66e302ee7963735 unverified MIT (permissive)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 baofff/U-ViT/libs/uvit.py 7a7de2a8e080f047 ran · fixture could not drive it fingerprinted MIT (permissive)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 22 Oct 2020 BrianPulfer/PapersReimplementations/src/cv/vit/vit_torch.py 49c15b51568e396b ran · fixture could not drive it MIT (permissive)
Whitening for Self-Supervised Representation Learning 13 Jul 2020 dr4thmos/solo-learn-radio/solo/losses/mae.py 3e6a557bf1ad83d9 ran MIT (permissive)
arXiv:aaai_29391 Jiahuiqu/LDS2AE/model.py d0417fac9afe3175 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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