Home › Code › contrastive_loss

contrastive_loss

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

contrastive_loss appears in the code Syntology harvested for 80 papers, as 54 distinct code bodies found in 84 places (a place is one code body under one paper). At least one of them ran in 60 of the papers; 19 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 contrastive_loss 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 35 of the 54 distinct code bodies named contrastive_loss; 19 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
1ran · violated contract
13ran · our draft was wrong
5ran · fixture could not drive it
15ran
19unverified
19fingerprinted

Licence is a property of each copy, so it is counted per place: 40 of the 84 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

80 papers shown of 80, newest first; 84 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 16 papers added by Syntology; 5 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
Decoupled Vision-Language System for Multimodal Understanding and Generation added by Syntology 2026-08 (from id) YifanXu74/Libra/libra/models/clip/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Beyond Scale and Generation: Understanding Language Model-based Entity Matching added by Syntology 2026-07 (from id) Jantory/llm-trained-matcher/utils/models.py f5b6bd9807a07466 ran no licence file found · pointer only
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification added by Syntology 2026-07 (from id) fmenat/Co4Miss/comiss/models/losses.py 97e4ae1a2e7254bb ran no licence file found · pointer only
VTaMo: Video-Text Alignment Model for Sign Language Translation added by Syntology 2026-07 (from id) junyi2005/vtamo/vtamo/clip_loss.py 1f93c0f3bc1dd120 ran fingerprinted licence not identified · pointer only
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models added by Syntology 2026-06 (from id) KQL11/Deep-VRM/ms-swift/swift/plugin/loss.py 02dbdd50bfbcb0ae ran Apache-2.0 (permissive)
scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing added by Syntology 2026-06 (from id) XPgogogo/scLLM-DSC/model/model.py e5fdec8e06236e4d ran · our draft was wrong fingerprinted MIT (permissive)
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing added by Syntology 2026-06 (from id) tengxiao1/GraphACL/hete/model.py bd248e252b9ee711 ran · fixture could not drive it fingerprinted no licence file found · pointer only
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents added by Syntology 2026-05 (from id) DeepExperience/HyperEyes/SFT/ms-swift-hypereyes/swift/plugin/loss.py 02dbdd50bfbcb0ae ran no licence file found · pointer only
A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation added by Syntology 2026-04 (from id) YBZh/CheXOne/swift/plugin/loss.py 02dbdd50bfbcb0ae ran Apache-2.0 (permissive)
Beyond Expression Similarity: Contrastive Learning Recovers Functional Gene Associations from Protein Interaction Structure added by Syntology 2026-03 (from id) EridosAI/GeneticCAL/paper/strengthening_results/run_01_node_split.py cffe9ba22ca505ad unverified MIT (permissive)
One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning added by Syntology 2026-03 (from id) xiaoyanzhang1/One-A/models/onea.py 402c4823b108bebc ran · our draft was wrong fingerprinted MIT (permissive)
Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning added by Syntology 2026-02 (from id) KoheiObata/MoST/models/losses.py af74d156c2e5a696 unverified no licence file found · pointer only
VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval added by Syntology 2026-02 (from id) dmgcsilva/vigia/inference/model.py 83ada93fd84968cc ran · our draft was wrong fingerprinted no licence file found · pointer only
MultiModal Fine-tuning with Synthetic Captions added by Syntology 2026-01 (from id) s-enmt/MMFT/utils/model_utils.py 0104870a9a95d4ea unverified licence not identified · pointer only
BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding added by Syntology 2026-01 (from id) Marloweeee/BARE/utils/loss_utils.py f2e5f28608115fa6 ran · honoured contract fingerprinted no licence file found · pointer only
DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models added by Syntology 2025-10 (from id) perceivelab/dexter/dexter/models/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted no licence file found · pointer only
RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction 7 Jul 2025 fraunhoferhhi/RIPE/ripe/losses/contrastive_loss.py 254d77ae91c12582 unverified licence not identified · pointer only
Static Word Embeddings for Sentence Semantic Representation 5 Jun 2025 twadada/swe4semantics/train_xling.py bc033863eb7b03a6 unverified Apache-2.0 (permissive)
arXiv:2505.21040 2025-05 (from id) cwei01/FCKT/bert/sentiment_modeling.py 82af44c9519a2dbf ran · our draft was wrong fingerprinted no licence file found · pointer only
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs 19 May 2025 case-lab-umd/llm-auditing-coin/3_Block2Answer/train/loss_func.py 37e51a6ba577d8d9 unverified MIT (permissive)
FG-CLIP: Fine-Grained Visual and Textual Alignment 8 May 2025 360CVGroup/FG-CLIP/fgclip2/model/strcs/fgclip2.py 54554dd514ac8105 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Cornstarch: Distributed Multimodal Training Must Be Multimodality-Aware 2025-03 (from id) cornstarch-org/Cornstarch/cornstarch/models/evaclip/modeling_evaclip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs 20 Feb 2025 dannigt/mid-align/src/transformers/models/align/modeling_align.py d1d7fb60f123d370 ran · our draft was wrong fingerprinted no licence file found · pointer only
Towards Utilising a Range of Neural Activations for Comprehending Representational Associations 15 Nov 2024 lauraaisling/MID-level-activations/src/dsprites/models.py 01e8f7f7f94c0bb5 unverified no licence file found · pointer only
TaxaBind: A Unified Embedding Space for Ecological Applications 1 Nov 2024 mvrl/taxabind/TaxaBind/EnvBind/model.py b000c0bc5e72377c unverified Apache-2.0 (permissive)
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models 29 Oct 2024 raman1121/diffusion_memorization_hpo/difffit/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted no licence file found · pointer only
PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion 14 Oct 2024 runsong123/pcf-lift/code/model/loss/loss.py 7cfbd12778d9a0db ran fingerprinted no licence file found · pointer only
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs 9 Oct 2024 identical code first harvested elsewhere 4675779aec92d6c0 ran · our draft was wrong fingerprinted licence of this copy not recorded
Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models 4 Oct 2024 Yufang-Liu/clip_hallucination/finetune_clip/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted no licence file found · pointer only
Preserving Generalization of Language models in Few-shot Continual Relation Extraction 1 Oct 2024 thanhnx12/CRE-via-MMI/SCKD/main-llm-mmi.py 4c858d28c511c74d ran fingerprinted no licence file found · pointer only
Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval 30 Sep 2024 lijiabei-7/leccr/LECCR/models/clip_vit.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted no licence file found · pointer only
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm 30 Sep 2024 bingqingzhang/TokenBinder/src/modeling/CLIP.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning 24 Sep 2024 william-wang618/m2pt/M2PT/model/llava_archPT.py 35caa662e2a8cf43 ran · our draft was wrong fingerprinted no licence file found · pointer only
M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework 9 Sep 2024 HongyangLL/M3-JEPA/src/loss_function.py 00d89ba2499c5d31 ran fingerprinted Apache-2.0 (permissive)
Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition 19 Jun 2024 azzh1/PURLS/model/utils/losses.py 29ad04a5f041d9d1 ran BSD-3-Clause (permissive)
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation 17 Jun 2024 kaist-cvml-lab/part-clipseg/transformers/models/clipseg/modeling_clipseg.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits 6 Jun 2024 pmzzs/JigMark/utils.py 224b2a54606c71f2 ran MIT (permissive)
Libra: Building Decoupled Vision System on Large Language Models 16 May 2024 yifanxu74/libra/libra/models/clip/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval 5 May 2024 miccunifi/searle/src/utils.py f96edb7ca8fe54fe unverified licence not identified · pointer only
Grounding Language Models for Visual Entity Recognition 28 Feb 2024 MrZilinXiao/AutoVER/LLaVA/llava/model/language_model/llava_llama.py 83ada93fd84968cc ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
UniVS: Unified and Universal Video Segmentation with Prompts as Queries 28 Feb 2024 minghanli/univs/univs/univs_prompt_longvideo.py bb2f0ddf9840604b ran no licence file found · pointer only
Explaining generative diffusion models via visual analysis for interpretable decision-making process 16 Feb 2024 ian-jihoonpark/X-Diffusion/models/clip_encoder.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted no licence file found · pointer only
Lite-Mind: Towards Efficient and Robust Brain Representation Network 6 Dec 2023 gongzix/lite-mind/src/engine.py 35caa662e2a8cf43 ran · our draft was wrong fingerprinted no licence file found · pointer only
StoryGPT-V: Large Language Models as Consistent Story Visualizers 4 Dec 2023 xiaoqian-shen/StoryGPT-V/gill/losses.py 83ada93fd84968cc ran · our draft was wrong fingerprinted no licence file found · pointer only
Language-only Efficient Training of Zero-shot Composed Image Retrieval 4 Dec 2023 navervision/lincir/utils.py f96edb7ca8fe54fe unverified no licence file found · pointer only
Zero-shot audio captioning with audio-language model guidance and audio context keywords 14 Nov 2023 explainableml/zeraucap/audio_captioning/language_model/loss_func.py dbe18b03333fa2bc ran no licence file found · pointer only
Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data 31 Oct 2023 a-antoniades/neuroformer/neuroformer/modules.py d496ef53516a57ca ran MIT (permissive)
Simple and Asymmetric Graph Contrastive Learning without Augmentations 29 Oct 2023 tengxiao1/graphacl/hete/model.py bd248e252b9ee711 ran · fixture could not drive it fingerprinted no licence file found · pointer only
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series 21 Oct 2023 dl4mhealth/comet/comet.py 016be840858ae4f4 ran MIT (permissive)
Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks 16 Oct 2023 gongchenghua/self-pro/Self-Pro/hete/model.py 68394def69dae059 ran no licence file found · pointer only
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation 28 Sep 2023 guyyariv/TempoTokens/modules/text_encoder/modeling_clip_tempotokens.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
Stable Diffusion is Unstable 5 Jun 2023 duchengbin8/Stable_Diffusion_is_Unstable/m_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation 22 May 2023 guyyariv/AudioToken/modules/clip_text_model/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
Improving Continual Relation Extraction by Distinguishing Analogous Semantics 11 May 2023 nju-websoft/CEAR/aca.py ec1bb1ccd4ab4788 ran · our draft was wrong GPL-3.0 (copyleft) · pointer only
Caption Anything: Interactive Image Description with Diverse Multimodal Controls 4 May 2023 ttengwang/caption-anything/caption_anything/captioner/modeling_blip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted BSD-3-Clause (permissive)
Grounding Language Models to Images for Multimodal Inputs and Outputs 31 Jan 2023 kohjingyu/fromage/fromage/losses.py 83ada93fd84968cc ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning 14 Oct 2022 swaggy-tn/efficientvlm/efficient_models/eff_vit.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted BSD-3-Clause recorded; this copy not marked cleared · pointer only
Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision 6 Oct 2022 JieyuZ2/wrench/wrench/endmodel/cosine.py 8c515f7346076b72 unverified Apache-2.0 (permissive)
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models 3 Oct 2022 1adrianb/lasp/prompting/losses.py 321f0835087b7e17 unverified MIT (permissive)
Multimodal Analogical Reasoning over Knowledge Graphs 1 Oct 2022 zjunlp/MKGformer/MKG/models/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
Multimodal Analogical Reasoning over Knowledge Graphs 1 Oct 2022 zjunlp/MKG_Analogy/MarT/models/modeling_clip.py f2e5f28608115fa6 ran · honoured contract fingerprinted MIT (permissive)
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment 14 Sep 2022 microsoft/xpretrain/CLIP-ViP/src/modeling/CLIP_ViP.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted licence not identified · pointer only
Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning 30 Aug 2022 microsoft/binder/src/model.py f7b4bc846f7c354c ran · our draft was wrong MIT (permissive)
Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning 30 Aug 2022 microsoft/binder/src/model.py 73ac50d5341bf380 ran · our draft was wrong MIT (permissive)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training 1 Jun 2022 zengyan-97/cclm/models/clip_vit.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted BSD-3-Clause recorded; this copy not marked cleared · pointer only
A Contrastive Framework for Neural Text Generation 13 Feb 2022 yxuansu/magic/image_captioning/language_model/simctg.py 369dc33768fbe11b ran · fixture could not drive it fingerprinted no licence file found · pointer only
Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration 26 Aug 2021 soroushseifi/glimpse-attend-explore/network_functions.py 02fc85da8a06ad83 unverified no licence file found · pointer only
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning 2 Jul 2021 dido1998/CausalMBRL/cswm/models/losses.py 4d34bf6b39947167 unverified MIT (permissive)
Backdoor Attacks on Self-Supervised Learning 21 May 2021 UMBCvision/SSL-Backdoor/byol/methods/contrastive.py ba00312b3d5b70dc ran · fixture could not drive it MIT (permissive)
Learning Transferable Visual Models From Natural Language Supervision 26 Feb 2021 filipbasara0/simple-clip/simple_clip/clip.py 4ea4d130ce4030a1 ran · our draft was wrong fingerprinted MIT (permissive)
Cross-Modal Contrastive Learning for Text-to-Image Generation 12 Jan 2021 google-research/xmcgan_image_generation/xmcgan/libml/attention_lib.py ba3acab33b57ea69 ran · fixture could not drive it fingerprinted no licence file found · pointer only
Fourier Neural Operator for Parametric Partial Differential Equations 18 Oct 2020 sala-group/autows-bench-101/wrench/endmodel/cosine.py 8c515f7346076b72 unverified Apache-2.0 (permissive)
COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations 15 Jun 2020 xavierfav/coala/dual_ae_trainer.py 7567a11b33565b39 ran · fixture could not drive it fingerprinted MIT (permissive)
A Simple Framework for Contrastive Learning of Visual Representations 13 Feb 2020 mdiephuis/simclr/loss.py eb14839e65ee11cf ran fingerprinted MIT (permissive)
A Simple Framework for Contrastive Learning of Visual Representations 13 Feb 2020 htdt/self-supervised/methods/contrastive.py ba00312b3d5b70dc ran · fixture could not drive it no licence file found · pointer only
A Simple Framework for Contrastive Learning of Visual Representations 13 Feb 2020 asd08573064/SimCLR/train_SSL.py eac22c52c3120485 unverified MIT (permissive)
RoBERTa: A Robustly Optimized BERT Pretraining Approach 26 Jul 2019 viethoang1512/kpa/qs_kpa/baselines/tf_models.py a5f2db749ea77f58 unverified Apache-2.0 (permissive)
Learnable PINs: Cross-Modal Embeddings for Person Identity 2 May 2018 my-yy/learnable_pins/utils/pair_selection_util.py a0ad7c051c1dd85d ran · our draft was wrong no licence file found · pointer only
FaceNet: A Unified Embedding for Face Recognition and Clustering 12 Mar 2015 fpleoni/its_all_in_the_family/source/facenet_take_2.py a29f1f1ec7d76f42 ran · violated contract no licence file found · pointer only
Semi-Supervised Learning with Deep Generative Models 20 Jun 2014 trungnt13/odin-ai/odin/backend/losses.py b854e50d4482e652 unverified MIT (permissive)
arXiv:aaai_28565 zhangxulu1996/Compositional-Inversion/model/modeling_clip.py 4675779aec92d6c0 ran · our draft was wrong fingerprinted MIT (permissive)
arXiv:aaai_26259 stxupengyu/LSFA/contrastive.py 0574eb3c753300ed unverified MIT (permissive)
arXiv:2024.findings-emnlp.965 Chauncey-Jheng/PCRL-MRG/llama_recipes/models/PCRL_llama/modeling_PCRL_llama.py 512b42a683272e0d unverified Apache-2.0 (permissive)
arXiv:2023.findings-emnlp.698 tommytyc/RSVP/RSVP.py 1f867ab9eb1b3ddb 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