Home › Code › clip_gradients

clip_gradients

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

clip_gradients appears in the code Syntology harvested for 31 papers, as 4 distinct code bodies found in 31 places (a place is one code body under one paper). At least one of them ran in 28 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 clip_gradients 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 1 of the 4 distinct code bodies named clip_gradients; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
1ran
3unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 4 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

31 papers shown of 31, 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; 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
CM3AE: A Unified RGB Frame and Event-Voxel/-Frame Pre-training Framework 17 Apr 2025 event-ahu/cm3ae/utils.py 2b5489053b222e00 ran MIT (permissive)
Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study 23 Oct 2024 ibm/dolomite-engine/lm_engine/kernels/torch_utils.py be3f8284e0ad756c unverified Apache-2.0 (permissive)
Large-Scale 3D Medical Image Pre-training with Geometric Context Priors 13 Oct 2024 luffy03/large-scale-medical/VoComni/models/MiT_utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features 3 Jul 2024 sthalles/MaSSL/utils.py 2b5489053b222e00 ran no licence file found · pointer only
GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection 11 Jun 2024 hyao1/glad/dino/utils.py 2b5489053b222e00 ran MIT (permissive)
Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images 8 Jun 2024 Genentech/set-dino/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
Automatic Jailbreaking of the Text-to-Image Generative AI Systems 26 May 2024 Kim-Minseon/APGP/dino_utils.py 2b5489053b222e00 ran no licence file found · pointer only
Boosting Unsupervised Segmentation Learning 4 Apr 2024 alperensari/segmentation-tricks/utils.py 2b5489053b222e00 ran no licence file found · pointer only
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers 12 Mar 2024 shahaf-arica/CuVLER/dino/utils.py 2b5489053b222e00 ran MIT (permissive)
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation 3 Mar 2024 MICV-yonsei/EAGLE/src_EAGLE/dino/utils.py 2b5489053b222e00 ran MIT (permissive)
Memorization in Self-Supervised Learning Improves Downstream Generalization 19 Jan 2024 sprintml/memorizationssl/models/DINO/utils.py 2b5489053b222e00 ran MIT (permissive)
Text-Driven Image Editing via Learnable Regions 28 Nov 2023 yuanze-lin/Learnable_Regions/models/dino_utils.py 2b5489053b222e00 ran MIT (permissive)
SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation 27 Oct 2023 mc-lan/smooseg/models/dino/utils.py 2b5489053b222e00 ran no licence file found · pointer only
Decoupling Common and Unique Representations for Multimodal Self-supervised Learning 11 Sep 2023 zhu-xlab/dino-mm/models/dino/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
A Multidimensional Analysis of Social Biases in Vision Transformers 3 Aug 2023 jannik-brinkmann/social-biases-in-vision-transformers/src/embedding_extractors/models/dino/utils.py 2b5489053b222e00 ran MIT (permissive)
Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Model 19 May 2023 jasonppy/syllable-discovery/models/vit_utils.py 2b5489053b222e00 ran BSD-3-Clause (permissive)
De-coupling and De-positioning Dense Self-supervised Learning 29 Mar 2023 ztt1024/densessl/utils.py 2b5489053b222e00 ran MIT (permissive)
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning 23 Mar 2023 stegmuel/CrOC/utils/utils.py 2b5489053b222e00 ran MIT (permissive)
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation 16 Mar 2023 huitangtang/on_the_utility_of_synthetic_data/supervised_learning/utils.py 2b5489053b222e00 ran MIT (permissive)
A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation 19 Sep 2022 ponimatkin/ssl-vos/dino_utils.py 2b5489053b222e00 ran MIT (permissive)
Exploring Target Representations for Masked Autoencoders 8 Sep 2022 liuxingbin/dbot/evaluation/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
Mugs: A Multi-Granular Self-Supervised Learning Framework 27 Mar 2022 sail-sg/mugs/src/optimizer.py 3adab9891c1273b6 unverified Apache-2.0 (permissive)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences 16 Mar 2022 leggedrobotics/self_supervised_segmentation/stego/backbones/dino/utils.py 2b5489053b222e00 ran MIT (permissive)
Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring 24 Feb 2022 jasonppy/word-discovery/models/vit_utils.py 2b5489053b222e00 ran BSD-3-Clause (permissive)
Self-Distilled Self-Supervised Representation Learning 25 Nov 2021 hagiss/sdssl/utils.py 2b5489053b222e00 ran MIT (permissive)
PASS: An ImageNet replacement for self-supervised pretraining without humans 27 Sep 2021 facebookresearch/dino/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
XCiT: Cross-Covariance Image Transformers 17 Jun 2021 adrienangeli/dino/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation 24 Jul 2018 AyaLotfy/PReMVOS-trial/code/ReID_net/Util.py fe9c62a98e81d5ca unverified MIT (permissive)
arXiv:Zhou_Towards_Effective_Foundation_Model_Adaptation_for_Extreme_Cross-Domain_Few-Shot_Learning_ICCV_2025_paper NWPUZhoufei/FMA/dino_utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
arXiv:Sun_Pixel-level_Semantic_Correspondence_through_Layout-aware_Representation_Learning_and_Multi-scale_Matching_CVPR_2024_paper YXSUNMADMAX/LPMFlow/models/feature_backbones/utils.py 2b5489053b222e00 ran Apache-2.0 (permissive)
arXiv:136810551 YtongXie/UniMiSS-code/UniMiSS/utils.py 2b5489053b222e00 ran 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