Home › Code › gather_features

gather_features

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

gather_features appears in the code Syntology harvested for 78 papers, as 21 distinct code bodies found in 78 places (a place is one code body under one paper). At least one of them ran in 4 of the papers; 2 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 gather_features 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 4 of the 21 distinct code bodies named gather_features; 17 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
0ran · fixture could not drive it
1ran
17unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 39 of the 78 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

78 papers shown of 78, newest first; 78 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 7 papers added by Syntology; 2 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
Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding added by Syntology 2026-09 (from id) duasoi/Mind2Cloud/eeg_data_process/clip_loss.py 9ce4a1350299a417 unverified no licence file found · pointer only
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images added by Syntology 2026-09 (from id) JuzhengMiao/Spatial-FAD/open_clip_SpatialFAD/loss.py ddcbd45e940484ee unverified MIT (permissive)
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking added by Syntology 2026-05 (from id) LAION-AI/CLAP/src/laion_clap/clap_module/loss.py 9b31c784540df0d7 unverified CC0-1.0 (permissive)
TRACER: Persistent Regularization for Robust Multimodal Finetuning added by Syntology 2026-05 (from id) HesamAsad/TRACER/clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Autoregressive Visual Decoding from EEG Signals added by Syntology 2026-02 (from id) ddicee/avde/models/labram.py 689bf1cf525e2160 unverified no licence file found · pointer only
Multi-Perspective Subimage CLIP with Keyword Guidance for Remote Sensing Image-Text Retrieval added by Syntology 2026-01 (from id) Lcrucial1f/MPS-CLIP/models/mpsclip.py 97ccd29f6f9846bc ran · honoured contract fingerprinted Apache-2.0 (permissive)
Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classification added by Syntology 2026-01 (from id) WHU-USI3DV/TreeCLS/models/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis 25 Mar 2025 mirthai/med3dvlm/src/model/CLIP.py f78bb358bb60eef1 unverified MIT (permissive)
GeoLangBind: Unifying Earth Observation with Agglomerative Vision-Language Foundation Models 8 Mar 2025 xiong-zhitong/geolb-siglip/open_clip/src/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
Hidden in the Noise: Two-Stage Robust Watermarking for Images 5 Dec 2024 Kasraarabi/Hidden-in-the-Noise/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
FLAIR: VLM with Fine-grained Language-informed Image Representations 4 Dec 2024 explainableml/flair/src/flair/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models 29 Nov 2024 vaynexie/DRM/clip_m/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation 15 Nov 2024 zdk258/CorrCLIP/CorrCLIPv1/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
On Erroneous Agreements of CLIP Image Embeddings 7 Nov 2024 lst627/CLIP-Embeds/open_clip/src/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization 6 Nov 2024 Hannah1102/ROBIN/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
SMITE: Segment Me In TimE 24 Oct 2024 alimohammadiamirhossein/smite/src/latent_optimization.py bec020dc9147bb3b ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
What If the Input is Expanded in OOD Detection? 24 Oct 2024 tmlr-group/CoVer/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
TULIP: Token-length Upgraded CLIP 13 Oct 2024 ivonajdenkoska/tulip/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
SePPO: Semi-Policy Preference Optimization for Diffusion Alignment 7 Oct 2024 dwanzhang-ai/seppo/utils/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality 7 Oct 2024 ytaek-oh/fsc-clip/src/training/losses/loss.py b9b5c04cbd9445bc ran · violated contract licence not identified · pointer only
A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety 4 Oct 2024 ganglii/devsafety/src/train_eval/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images 2 Oct 2024 likyoo/SegEarth-OV/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
ImageFolder: Autoregressive Image Generation with Folded Tokens 2 Oct 2024 lxa9867/imagefolder/tokenizer/tokenizer_image/cliploss.py ddcbd45e940484ee unverified licence not identified · pointer only
Embedding Geometries of Contrastive Language-Image Pre-Training 19 Sep 2024 eify/open_clip/src/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis 16 Aug 2024 YubaoZhao/ECG-Chat/open_clip/open_clip/loss.py e3d14dccb8dfdb3d unverified no licence file found · pointer only
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation 9 Aug 2024 mc-lan/proxyclip/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
VSSD: Vision Mamba with Non-Causal State Space Duality 26 Jul 2024 YuHengsss/Trident/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model 9 Jul 2024 leexinhao/VideoEval/VidTAB_Zeroshot/eva_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion 3 Jul 2024 WHU-USI3DV/EGIInet/models/layers/graph_conv.py e6ba453e7cc8da17 ran MIT (permissive)
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP 25 Jun 2024 sarahesl/alignclip/align_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning 11 Jun 2024 opengvlab/lcl/src/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs 11 Jun 2024 damo-nlp-sg/inf-clip/inf_clip/models/loss.py 9ad02daca617f28b unverified Apache-2.0 (permissive)
RWKV-CLIP: A Robust Vision-Language Representation Learner 11 Jun 2024 deepglint/RWKV-CLIP/loss.py ddcbd45e940484ee unverified MIT (permissive)
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better 7 Jun 2024 scottgeng00/unmet-promise/adapt/clip_custom/loss.py ddcbd45e940484ee unverified MIT (permissive)
Prompt-guided Precise Audio Editing with Diffusion Models 11 May 2024 haoheliu/audioldm/audioldm/clap/open_clip/loss.py 9b31c784540df0d7 unverified no licence file found · pointer only
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale 27 May 2024 3dlg-hcvc/bioscan-clip/bioscanclip/model/loss_func.py 89968f9743af3ef4 unverified MIT (permissive)
Efficient Vision-Language Pre-training by Cluster Masking 14 May 2024 zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Modeling Caption Diversity in Contrastive Vision-Language Pretraining 30 Apr 2024 facebookresearch/llip/llip/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
PuLID: Pure and Lightning ID Customization via Contrastive Alignment 24 Apr 2024 tothebeginning/pulid/eva_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification 22 Apr 2024 showlab/ringid/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization 21 Apr 2024 casia-iva-lab/filo/models/vv_open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection 8 Apr 2024 funz-0/promptad/PromptAD/CLIPAD/loss.py ddcbd45e940484ee unverified Unlicense (permissive)
Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models 7 Apr 2024 bsmhmmlf/Gaussian-Shading/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
ViTamin: Designing Scalable Vision Models in the Vision-Language Era 2 Apr 2024 beckschen/vitamin/ViTamin/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
DreamLIP: Language-Image Pre-training with Long Captions 25 Mar 2024 zyf0619sjtu/DreamLIP/open_clip/loss.py ddcbd45e940484ee unverified CC-BY-4.0 · pointer only
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction 25 Mar 2024 citymind-lab/urbanvlp/open_clip_mine/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Long-CLIP: Unlocking the Long-Text Capability of CLIP 22 Mar 2024 beichenzbc/long-clip/open_clip_long/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
Improving Medical Multi-modal Contrastive Learning with Expert Annotations 15 Mar 2024 ykumards/eclip/eclip/model/eclip_module.py 4b7fdd1c6930c4d9 unverified AGPL-3.0 (copyleft) · pointer only
Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts 11 Mar 2024 mala-lab/WinCLIP/open_clip/loss.py ddcbd45e940484ee unverified GPL-3.0 (copyleft) · pointer only
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively 5 Jan 2024 harboryuan/ovsam/ext/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing 20 Dec 2023 wangzhecheng/skyscript/src/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
UniChest: Conquer-and-Divide Pre-training for Multi-Source Chest X-Ray Classification 18 Dec 2023 elfenreigen/unichest/factory/loss.py ddcbd45e940484ee unverified MIT (permissive)
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models 4 Dec 2023 xunguangwang/instructta/EVA-CLIP/rei/eva_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions 28 Nov 2023 show-han/zeroshot_rec/VLA_finetune/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 (permissive)
Diffusion Model Alignment Using Direct Preference Optimization 21 Nov 2023 SalesforceAIResearch/DiffusionDPO/utils/open_clip/loss.py ddcbd45e940484ee unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Towards Calibrated Robust Fine-Tuning of Vision-Language Models 3 Nov 2023 MLAI-Yonsei/CaRot/clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders 1 Nov 2023 antofuller/croma/pretrain_croma.py 816756cd7d531829 unverified MIT (permissive)
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection 29 Oct 2023 zqhang/WinCLIP-pytorch/src/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction 2 Oct 2023 wusize/clipself/src/open_clip/loss.py fd6321f5fd69ea0a unverified licence not identified · pointer only
Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization 30 Aug 2023 hq-deng/AnoVL/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
Fine-tuning can cripple your foundation model; preserving features may be the solution 25 Aug 2023 omegafragger/ldifs_code/loss/clip_loss.py ddcbd45e940484ee unverified MIT (permissive)
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No 23 Aug 2023 xmed-lab/CLIPN/hand-crafted/src/open_clip/loss.py 61c4ca21dc698a56 unverified MIT (permissive)
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining 10 Aug 2023 haoheliu/AudioLDM2/audioldm2/clap/open_clip/loss.py 9b31c784540df0d7 unverified no licence file found · pointer only
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts 2 Aug 2023 umd-huang-lab/perceptionCLIP/clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
CLIP-KD: An Empirical Study of CLIP Model Distillation 24 Jul 2023 winycg/clip-kd/src/open_clip/loss.py ddcbd45e940484ee unverified no licence file found · pointer only
LibAUC: A Deep Learning Library for X-Risk Optimization 5 Jun 2023 Optimization-AI/LibAUC/libauc/losses/contrastive.py 0e719e1b1ed02c5a unverified MIT (permissive)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD 27 May 2023 bychelsea/vand-april-gan/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training 17 Apr 2023 mlfoundations/open_clip/src/open_clip/loss.py e105065a1a8c0e5a unverified licence not identified · pointer only
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation 26 Mar 2023 caoyunkang/WinClip/WinCLIP/CLIPAD/loss.py ddcbd45e940484ee unverified MIT (permissive)
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents 13 Mar 2023 WeixiongLin/PMC-CLIP/src/pmc_clip/loss/utils.py 0425170c0cb7b081 unverified MIT (permissive)
Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations 27 Feb 2023 VITA-Group/layerGraftedPretraining_ICLR23/utils/pretrain.py 0cb11d4906fe4ba1 unverified licence not identified · pointer only
Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images 27 Feb 2023 xiaoman-zhang/kad/A3_CLIP/factory/loss.py ddcbd45e940484ee unverified MIT (permissive)
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery 7 Feb 2023 YuxinWenRick/hard-prompts-made-easy/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
Learning Customized Visual Models with Retrieval-Augmented Knowledge 17 Jan 2023 microsoft/react/react_customization/src/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
Learning Video Representations from Large Language Models 8 Dec 2022 facebookresearch/lavila/lavila/models/loss.py 19519e7e08dd0087 unverified MIT recorded; this copy not marked cleared · pointer only
Finetune like you pretrain: Improved finetuning of zero-shot vision models 1 Dec 2022 locuslab/flyp/clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
arXiv:Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper cshcma/ReMP-AD/open_clip/loss.py ddcbd45e940484ee unverified MIT (permissive)
arXiv:Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper aim-uofa/StyleDrop-PyTorch/open_clip/loss.py ddcbd45e940484ee 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