Home › Code › create_npz_from_sample_folder

create_npz_from_sample_folder

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

create_npz_from_sample_folder appears in the code Syntology harvested for 30 papers, as 11 distinct code bodies found in 31 places (a place is one code body under one paper). At least one of them ran in 26 of the papers; 0 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 create_npz_from_sample_folder 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 7 of the 11 distinct code bodies named create_npz_from_sample_folder; 4 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
4ran · our draft was wrong
0ran · fixture could not drive it
3ran
4unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 17 of the 31 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

30 papers shown of 30, newest first; 31 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 1 papers added by Syntology. 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
Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples added by Syntology 2026-01 (from id) WD7ang/VAR-Scaling/VAR-main/create_ngz.py 280dae1512c7b50f unverified MIT (permissive)
Contrastive Flow Matching 5 Jun 2025 identical code first harvested elsewhere 7b21a01ae77703a3 ran · our draft was wrong licence of this copy not recorded
AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model 5 Jun 2025 ali-vilab/alitok/sample_imagenet.py 19a5b88fdb546606 ran · our draft was wrong no licence file found · pointer only
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training 22 May 2025 identical code first harvested elsewhere 7b21a01ae77703a3 ran · our draft was wrong licence of this copy not recorded
PixelFlow: Pixel-Space Generative Models with Flow 10 Apr 2025 shoufachen/pixelflow/sample_ddp.py c43ca4c65f3079a7 ran · our draft was wrong MIT (permissive)
Autoregressive Image Generation with Randomized Parallel Decoding 13 Mar 2025 hp-l33/ARPG/sample_c2i_ddp.py 7b21a01ae77703a3 ran · our draft was wrong MIT (permissive)
DiC: Rethinking Conv3x3 Designs in Diffusion Models 31 Dec 2024 identical code first harvested elsewhere 7b21a01ae77703a3 ran · our draft was wrong licence of this copy not recorded
Causal Diffusion Transformers for Generative Modeling 16 Dec 2024 causalfusion/causalfusion/sample.py 84e2a647a1c4db79 ran · our draft was wrong no licence file found · pointer only
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising 7 Dec 2024 vainf/remix-dit/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
TinyFusion: Diffusion Transformers Learned Shallow 2 Dec 2024 vainf/tinyfusion/sample_ddp.py 404991021d3508d4 unverified licence not identified · pointer only
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient 26 Nov 2024 czg1225/code/sample_CoDe.py 78f71e05e187283b unverified MIT (permissive)
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints 26 Nov 2024 opensparsellms/skip-dit/class-to-image/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong Apache-2.0 (permissive)
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching 31 Oct 2024 identical code first harvested elsewhere 7b21a01ae77703a3 ran · our draft was wrong licence of this copy not recorded
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment 12 Oct 2024 thu-ml/cca/LlamaGen_sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong MIT (permissive)
Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment 12 Oct 2024 thu-ml/cca/VAR_sample.py 4f771efa92658445 ran MIT (permissive)
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think 9 Oct 2024 sihyun-yu/REPA/generate.py 7b21a01ae77703a3 ran · our draft was wrong MIT (permissive)
Dynamic Diffusion Transformer 4 Oct 2024 nus-hpc-ai-lab/dynamic-diffusion-transformer/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
ControlAR: Controllable Image Generation with Autoregressive Models 3 Oct 2024 hustvl/ControlAR/create_npz.py 432162d12f959985 ran Apache-2.0 (permissive)
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner 26 Sep 2024 shiml20/FlowTurbo/sample_ddp_feature.py fa92e506df16d054 unverified MIT (permissive)
MonoFormer: One Transformer for Both Diffusion and Autoregression 24 Sep 2024 MonoFormer/MonoFormer/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models 16 Sep 2024 yuchuantian/u-dit/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing 12 Sep 2024 DZY122/DiTAS/sample_merge_TAS.py c43ca4c65f3079a7 ran · our draft was wrong MIT (permissive)
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators 11 Aug 2024 leaplabthu/attention-mediators/attention_mediator/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
Scaling Diffusion Transformers to 16 Billion Parameters 16 Jul 2024 feizc/dit-moe/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
FORA: Fast-Forward Caching in Diffusion Transformer Acceleration 1 Jul 2024 prathebaselva/fora/src/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers 25 Jun 2024 identical code first harvested elsewhere 19a5b88fdb546606 ran · our draft was wrong licence of this copy not recorded
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers 4 May 2024 identical code first harvested elsewhere 7b21a01ae77703a3 ran · our draft was wrong licence of this copy not recorded
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts 14 Mar 2024 byeongjun-park/Switch-DiT/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong MIT (permissive)
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching 21 Feb 2024 nvlabs/t-stitch/dit/sample_ddp_t_stitch.py 7b21a01ae77703a3 ran · our draft was wrong no licence file found · pointer only
FiT: Flexible Vision Transformer for Diffusion Model 19 Feb 2024 whlzy/fit/fit/utils/eval_utils.py 7a6ba78116641182 ran Apache-2.0 (permissive)
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers 16 Jan 2024 willisma/sit/sample_ddp.py 7b21a01ae77703a3 ran · our draft was wrong 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