{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/clip","slug":"clip","name":"CLIP","full_name":"Contrastive Language-Image Pre-training","full_name_withheld":false,"description_markdown":"**Contrastive Language-Image Pre-training** (**CLIP**), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning from natural language supervision. , CLIP jointly trains an image encoder and a text encoder to predict the correct pairings of a batch of (image, text) training examples. At test time the learned text encoder synthesizes a zero-shot linear classifier by embedding the names or descriptions of the target dataset’s classes. \r\n\r\nFor pre-training, CLIP is trained to predict which of the $N X N$ possible (image, text) pairings across a batch actually occurred. CLIP learns a multi-modal embedding space by jointly training an image encoder and text encoder to maximize the cosine similarity of the image and text embeddings of the $N$ real pairs in the batch while minimizing the cosine similarity of the embeddings of the $N^2 - N$ incorrect pairings. A symmetric cross entropy loss is optimized over these similarity scores. \r\n\r\nImage credit: [Learning Transferable Visual Models From Natural Language Supervision](https://arxiv.org/pdf/2103.00020.pdf)","description_state":"present","introduced_year":null,"introduced_by":{"title":"Learning Transferable Visual Models From Natural Language Supervision","paper":"/paper/learning-transferable-visual-models-from","first_author":"Alec Radford","n_authors":12,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/learning-transferable-visual-models-from"},"source":{"url":"https://arxiv.org/abs/2103.00020v1","title":"Learning Transferable Visual Models From Natural Language Supervision","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/OpenAI/CLIP","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Representations","url":"/methods/category/image-representations","pwc_aliases":[]}],"n_papers_tagged":3094,"archive_num_papers":3094,"papers_newest_first":[{"paper":null,"slug":"bridge-feature-matching-and-cross-modal","title":"Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection","date":"2025-07-15","arxiv_id":"2507.11003","n_code_links":0,"syntology":null},{"paper":null,"slug":"catvis-context-aware-thought-visualization","title":"CATVis: Context-Aware Thought Visualization","date":"2025-07-15","arxiv_id":"2507.11522","n_code_links":0,"syntology":null},{"paper":"/paper/dearli-decoupled-enhancement-of-recognition","slug":"dearli-decoupled-enhancement-of-recognition","title":"DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation","date":"2025-07-14","arxiv_id":"2507.10118","n_code_links":1,"syntology":null},{"paper":"/paper/test-time-canonicalization-by-foundation","slug":"test-time-canonicalization-by-foundation","title":"Test-Time Canonicalization by Foundation Models for Robust Perception","date":"2025-07-14","arxiv_id":"2507.10375","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sutkarsh/focal"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-visual-semantic-constrained-ai-generated","slug":"text-visual-semantic-constrained-ai-generated","title":"Text-Visual Semantic Constrained AI-Generated Image Quality Assessment","date":"2025-07-14","arxiv_id":"2507.10432","n_code_links":1,"syntology":null},{"paper":null,"slug":"calibrated-and-robust-foundation-models-for","title":"Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift","date":"2025-07-12","arxiv_id":"2507.09222","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-representation-framework-with-llm","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","date":"2025-07-09","arxiv_id":"2507.06719","n_code_links":0,"syntology":null},{"paper":"/paper/cultureclip-empowering-clip-with-cultural","slug":"cultureclip-empowering-clip-with-cultural","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","date":"2025-07-08","arxiv_id":"2507.06210","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":4,"n_instrument":5,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["lukahhcm/cultureclip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"integrated-structural-prompt-learning-for","title":"Integrated Structural Prompt Learning for Vision-Language Models","date":"2025-07-08","arxiv_id":"2507.05677","n_code_links":0,"syntology":null},{"paper":"/paper/rsrefseg-2-decoupling-referring-remote","slug":"rsrefseg-2-decoupling-referring-remote","title":"RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models","date":"2025-07-08","arxiv_id":"2507.06231","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-defect-detection-via","slug":"semi-supervised-defect-detection-via","title":"Semi-Supervised Defect Detection via Conditional Diffusion and CLIP-Guided Noise Filtering","date":"2025-07-08","arxiv_id":"2507.05588","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-vision-language-models-for","title":"An analysis of vision-language models for fabric retrieval","date":"2025-07-07","arxiv_id":"2507.04735","n_code_links":0,"syntology":null},{"paper":"/paper/clip-guided-backdoor-defense-through-entropy","slug":"clip-guided-backdoor-defense-through-entropy","title":"CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation","date":"2025-07-07","arxiv_id":"2507.05113","n_code_links":1,"syntology":null},{"paper":"/paper/pfedmma-personalized-federated-fine-tuning","slug":"pfedmma-personalized-federated-fine-tuning","title":"pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models","date":"2025-07-07","arxiv_id":"2507.05394","n_code_links":1,"syntology":{"ran":4,"of":11,"n_ran_checked":1,"n_instrument":3,"unverified":7,"pointer_only":11,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["sajjad-ucsb/pfedmma"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-accuracy-metrics-that-uncover-what","slug":"beyond-accuracy-metrics-that-uncover-what","title":"Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor","date":"2025-07-04","arxiv_id":"2507.03542","n_code_links":1,"syntology":null},{"paper":null,"slug":"helping-clip-see-both-the-forest-and-the","title":"Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach","date":"2025-07-04","arxiv_id":"2507.03458","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-disentanglement-via-language-guidance","title":"Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization","date":"2025-07-03","arxiv_id":"2507.02288","n_code_links":0,"syntology":null},{"paper":null,"slug":"votesplat-hough-voting-gaussian-splatting-for","title":"VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding","date":"2025-06-28","arxiv_id":"2506.22799","n_code_links":0,"syntology":null},{"paper":null,"slug":"q-frame-query-aware-frame-selection-and-multi","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","date":"2025-06-27","arxiv_id":"2506.22139","n_code_links":0,"syntology":null},{"paper":null,"slug":"little-by-little-continual-learning-via-self","title":"Little By Little: Continual Learning via Self-Activated Sparse Mixture-of-Rank Adaptive Learning","date":"2025-06-26","arxiv_id":"2506.21035","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-hallucination-of-large-vision","slug":"mitigating-hallucination-of-large-vision","title":"Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration","date":"2025-06-26","arxiv_id":"2506.21509","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-prompt-alignment-for-facial","title":"Multimodal Prompt Alignment for Facial Expression Recognition","date":"2025-06-26","arxiv_id":"2506.21017","n_code_links":0,"syntology":null},{"paper":"/paper/reme-a-data-centric-framework-for-training","slug":"reme-a-data-centric-framework-for-training","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","date":"2025-06-26","arxiv_id":"2506.21233","n_code_links":1,"syntology":null},{"paper":"/paper/sharpzo-hybrid-sharpness-aware-vision","slug":"sharpzo-hybrid-sharpness-aware-vision","title":"SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes","date":"2025-06-26","arxiv_id":"2506.20990","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":1,"n_instrument":5,"unverified":4,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yifanycc/sharpzo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-vision-language-models-to-select","title":"Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models","date":"2025-06-25","arxiv_id":"2506.20832","n_code_links":0,"syntology":null},{"paper":null,"slug":"unfolding-the-past-a-comprehensive-deep","title":"Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages","date":"2025-06-22","arxiv_id":"2506.18069","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-political-bias-identification-and","title":"Multimodal Political Bias Identification and Neutralization","date":"2025-06-20","arxiv_id":"2506.17372","n_code_links":0,"syntology":null},{"paper":null,"slug":"prmpt2adpt-prompt-based-zero-shot-domain","title":"Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments","date":"2025-06-20","arxiv_id":"2506.16994","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-common-vlms-rival-medical-vlms-evaluation","title":"Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights","date":"2025-06-19","arxiv_id":"2506.17337","n_code_links":0,"syntology":null},{"paper":"/paper/evolutionary-caching-to-accelerate-your-off","slug":"evolutionary-caching-to-accelerate-your-off","title":"Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model","date":"2025-06-18","arxiv_id":"2506.15682","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aniaggarwal/ecad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/eva02-at-egocentric-video-language","slug":"eva02-at-egocentric-video-language","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","date":"2025-06-17","arxiv_id":"2506.14356","n_code_links":1,"syntology":null},{"paper":null,"slug":"unified-representation-space-for-3d-visual","title":"Unified Representation Space for 3D Visual Grounding","date":"2025-06-17","arxiv_id":"2506.14238","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-the-box-reasoning-about-unseen","title":"What's in the Box? Reasoning about Unseen Objects from Multimodal Cues","date":"2025-06-17","arxiv_id":"2506.14212","n_code_links":0,"syntology":null},{"paper":null,"slug":"freeq-graph-free-form-querying-with-semantic","title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","date":"2025-06-16","arxiv_id":"2506.13629","n_code_links":0,"syntology":null},{"paper":null,"slug":"otfusion-bridging-vision-only-and-vision","title":"OTFusion: Bridging Vision-only and Vision-Language Models via Optimal Transport for Transductive Zero-Shot Learning","date":"2025-06-16","arxiv_id":"2506.13723","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-structure-in-clip-embeddings-a","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","date":"2025-06-16","arxiv_id":"2506.13831","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantitative-comparison-of-fine-tuning","title":"Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Image Concepts","date":"2025-06-16","arxiv_id":"2506.13307","n_code_links":0,"syntology":null},{"paper":null,"slug":"nap-tuning-neural-augmented-prompt-tuning-for","title":"NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models","date":"2025-06-15","arxiv_id":"2506.12706","n_code_links":0,"syntology":null},{"paper":null,"slug":"invertune-removing-backdoors-from-multimodal","title":"InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning","date":"2025-06-14","arxiv_id":"2506.12411","n_code_links":0,"syntology":null},{"paper":"/paper/clip-the-landscape-automated-tagging-of","slug":"clip-the-landscape-automated-tagging-of","title":"CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images","date":"2025-06-13","arxiv_id":"2506.12214","n_code_links":1,"syntology":null},{"paper":null,"slug":"visage-video-to-spatial-audio-generation","title":"ViSAGe: Video-to-Spatial Audio Generation","date":"2025-06-13","arxiv_id":"2506.12199","n_code_links":0,"syntology":null},{"paper":"/paper/2506-10540","slug":"2506-10540","title":"AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation","date":"2025-06-12","arxiv_id":"2506.10540","n_code_links":1,"syntology":null},{"paper":"/paper/air-zero-shot-generative-model-adaptation","slug":"air-zero-shot-generative-model-adaptation","title":"AIR: Zero-shot Generative Model Adaptation with Iterative Refinement","date":"2025-06-12","arxiv_id":"2506.10895","n_code_links":1,"syntology":null},{"paper":"/paper/iqe-clip-instance-aware-query-embedding-for","slug":"iqe-clip-instance-aware-query-embedding-for","title":"IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain","date":"2025-06-12","arxiv_id":"2506.10730","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-to-image-for-multi-label-image","title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning","date":"2025-06-12","arxiv_id":"2506.10575","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-sample-complexity-of-parameter-free","title":"The Sample Complexity of Parameter-Free Stochastic Convex Optimization","date":"2025-06-12","arxiv_id":"2506.11336","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-aware-deep-learning-for-automated","title":"Uncertainty-Aware Deep Learning for Automated Skin Cancer Classification: A Comprehensive Evaluation","date":"2025-06-12","arxiv_id":"2506.10302","n_code_links":0,"syntology":null},{"paper":"/paper/2506-10172","slug":"2506-10172","title":"A Navigation Framework Utilizing Vision-Language Models","date":"2025-06-11","arxiv_id":"2506.10172","n_code_links":1,"syntology":null},{"paper":"/paper/adding-simple-structure-at-inference-improves","slug":"adding-simple-structure-at-inference-improves","title":"Adding simple structure at inference improves Vision-Language Compositionality","date":"2025-06-11","arxiv_id":"2506.09691","n_code_links":1,"syntology":null},{"paper":null,"slug":"harmonizing-and-merging-source-models-for","title":"Harmonizing and Merging Source Models for CLIP-based Domain Generalization","date":"2025-06-11","arxiv_id":"2506.09446","n_code_links":0,"syntology":null},{"paper":null,"slug":"adam-autonomous-discovery-and-annotation","title":"ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotations","date":"2025-06-10","arxiv_id":"2506.08968","n_code_links":0,"syntology":null},{"paper":null,"slug":"atas-any-to-any-self-distillation-for","title":"ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction","date":"2025-06-10","arxiv_id":"2506.08678","n_code_links":0,"syntology":null},{"paper":"/paper/discovla-discrepancy-reduction-in-vision-1","slug":"discovla-discrepancy-reduction-in-vision-1","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","date":"2025-06-10","arxiv_id":"2506.08887","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lunarshen/dsicovla"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fusing-cross-modal-and-uni-modal","title":"Fusing Cross-modal and Uni-modal Representations: A Kronecker Product Approach","date":"2025-06-10","arxiv_id":"2506.08645","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-of-decoder-only-llms-1","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","date":"2025-06-09","arxiv_id":"2506.08210","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-good-crepe-needs-more-than-just-sugar","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","date":"2025-06-09","arxiv_id":"2506.08227","n_code_links":0,"syntology":null},{"paper":"/paper/circumventing-backdoor-space-via-weight","slug":"circumventing-backdoor-space-via-weight","title":"Circumventing Backdoor Space via Weight Symmetry","date":"2025-06-09","arxiv_id":"2506.07467","n_code_links":1,"syntology":null},{"paper":"/paper/highly-compressed-tokenizer-can-generate","slug":"highly-compressed-tokenizer-can-generate","title":"Highly Compressed Tokenizer Can Generate Without Training","date":"2025-06-09","arxiv_id":"2506.08257","n_code_links":1,"syntology":null},{"paper":"/paper/vision-transformers-don-t-need-trained","slug":"vision-transformers-don-t-need-trained","title":"Vision Transformers Don't Need Trained Registers","date":"2025-06-09","arxiv_id":"2506.08010","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nickjiang2378/test-time-registers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vivat-virtuous-improving-vae-training-through","title":"VIVAT: Virtuous Improving VAE Training through Artifact Mitigation","date":"2025-06-09","arxiv_id":"2506.07863","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-narrative-review-on-large-ai-models-in-lung","title":"A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning","date":"2025-06-08","arxiv_id":"2506.07236","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-static-image-sub","title":"Experimental Evaluation of Static Image Sub-Region-Based Search Models Using CLIP","date":"2025-06-07","arxiv_id":"2506.06938","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-state-of-the-art-in-lifelog-retrieval-a","title":"The State-of-the-Art in Lifelog Retrieval: A Review of Progress at the ACM Lifelog Search Challenge Workshop 2022-24","date":"2025-06-07","arxiv_id":"2506.06743","n_code_links":0,"syntology":null},{"paper":null,"slug":"noise-consistency-regularization-for-improved","title":"Noise Consistency Regularization for Improved Subject-Driven Image Synthesis","date":"2025-06-06","arxiv_id":"2506.06483","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-cropped-regions-new-benchmark-and","title":"Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts","date":"2025-06-05","arxiv_id":"2506.04999","n_code_links":0,"syntology":null},{"paper":null,"slug":"handle-based-mesh-deformation-guided-by","title":"Handle-based Mesh Deformation Guided By Vision Language Model","date":"2025-06-05","arxiv_id":"2506.04562","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-laws-for-robust-comparison-of-open","slug":"scaling-laws-for-robust-comparison-of-open","title":"Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets","date":"2025-06-05","arxiv_id":"2506.04598","n_code_links":2,"syntology":null},{"paper":"/paper/tuning-the-right-foundation-models-is-what","slug":"tuning-the-right-foundation-models-is-what","title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","date":"2025-06-05","arxiv_id":"2506.05027","n_code_links":1,"syntology":null},{"paper":null,"slug":"normalize-filters-classical-wisdom-for-deep","title":"Normalize Filters! Classical Wisdom for Deep Vision","date":"2025-06-04","arxiv_id":"2506.04401","n_code_links":0,"syntology":null},{"paper":"/paper/attacking-attention-of-foundation-models","slug":"attacking-attention-of-foundation-models","title":"Attacking Attention of Foundation Models Disrupts Downstream Tasks","date":"2025-06-03","arxiv_id":"2506.05394","n_code_links":1,"syntology":null},{"paper":null,"slug":"flexiffusion-training-free-segment-wise","title":"Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models","date":"2025-06-03","arxiv_id":"2506.02488","n_code_links":0,"syntology":null},{"paper":"/paper/robustness-in-both-domains-clip-needs-a","slug":"robustness-in-both-domains-clip-needs-a","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","date":"2025-06-03","arxiv_id":"2506.03355","n_code_links":0,"syntology":{"ran":9,"of":12,"n_ran_checked":1,"n_instrument":8,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"advancing-compositional-awareness-in-clip","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","date":"2025-05-30","arxiv_id":"2505.24424","n_code_links":0,"syntology":null},{"paper":"/paper/conformal-prediction-for-zero-shot-models","slug":"conformal-prediction-for-zero-shot-models","title":"Conformal Prediction for Zero-Shot Models","date":"2025-05-30","arxiv_id":"2505.24693","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jusiro/clip-conformal"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/silvr-a-simple-language-based-video-reasoning","slug":"silvr-a-simple-language-based-video-reasoning","title":"SiLVR: A Simple Language-based Video Reasoning Framework","date":"2025-05-30","arxiv_id":"2505.24869","n_code_links":1,"syntology":null},{"paper":"/paper/un-2-clip-improving-clip-s-visual-detail","slug":"un-2-clip-improving-clip-s-visual-detail","title":"un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP","date":"2025-05-30","arxiv_id":"2505.24517","n_code_links":1,"syntology":null},{"paper":"/paper/adversarial-semantic-and-label-perturbation","slug":"adversarial-semantic-and-label-perturbation","title":"Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition","date":"2025-05-29","arxiv_id":"2505.23313","n_code_links":2,"syntology":null},{"paper":"/paper/cldtracker-a-comprehensive-language","slug":"cldtracker-a-comprehensive-language","title":"CLDTracker: A Comprehensive Language Description for Visual Tracking","date":"2025-05-29","arxiv_id":"2505.23704","n_code_links":1,"syntology":null},{"paper":null,"slug":"curve-clip-utilized-reinforcement-learning","title":"CURVE: CLIP-Utilized Reinforcement Learning for Visual Image Enhancement via Simple Image Processing","date":"2025-05-29","arxiv_id":"2505.23102","n_code_links":0,"syntology":null},{"paper":"/paper/deep-modeling-and-optimization-of-medical","slug":"deep-modeling-and-optimization-of-medical","title":"Deep Modeling and Optimization of Medical Image Classification","date":"2025-05-29","arxiv_id":"2505.23040","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-next-scale-visual-autoregressive","title":"Fine-Tuning Next-Scale Visual Autoregressive Models with Group Relative Policy Optimization","date":"2025-05-29","arxiv_id":"2505.23331","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-inversion-turns-clip-into-a-decoder","slug":"implicit-inversion-turns-clip-into-a-decoder","title":"Implicit Inversion turns CLIP into a Decoder","date":"2025-05-29","arxiv_id":"2505.23161","n_code_links":1,"syntology":null},{"paper":"/paper/lada-scalable-label-specific-clip-adapter-for","slug":"lada-scalable-label-specific-clip-adapter-for","title":"LADA: Scalable Label-Specific CLIP Adapter for Continual Learning","date":"2025-05-29","arxiv_id":"2505.23271","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["maolinluo/lada"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/qlip-a-dynamic-quadtree-vision-prior-enhances","slug":"qlip-a-dynamic-quadtree-vision-prior-enhances","title":"QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining","date":"2025-05-29","arxiv_id":"2505.23004","n_code_links":1,"syntology":null},{"paper":"/paper/scalelong-a-multi-timescale-benchmark-for","slug":"scalelong-a-multi-timescale-benchmark-for","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","date":"2025-05-29","arxiv_id":"2505.23922","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-entropy-mechanism-of-reinforcement","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","date":"2025-05-28","arxiv_id":"2505.22617","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-visual-encoder-learn-to-see-arrows","title":"Can Visual Encoder Learn to See Arrows?","date":"2025-05-26","arxiv_id":"2505.19944","n_code_links":0,"syntology":null},{"paper":null,"slug":"ccl-lgs-contrastive-codebook-learning-for-3d","title":"CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting","date":"2025-05-26","arxiv_id":"2505.20469","n_code_links":0,"syntology":null},{"paper":"/paper/correlating-instruction-tuning-in-multimodal","slug":"correlating-instruction-tuning-in-multimodal","title":"Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)","date":"2025-05-26","arxiv_id":"2505.20029","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["subbareddy248/mllm_instruction_brain"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"disa-directional-saliency-aware-prompt","title":"DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models","date":"2025-05-26","arxiv_id":"2505.19373","n_code_links":0,"syntology":null},{"paper":"/paper/from-what-to-how-attributing-clip-s-latent","slug":"from-what-to-how-attributing-clip-s-latent","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","date":"2025-05-26","arxiv_id":"2505.20229","n_code_links":1,"syntology":null},{"paper":"/paper/hard-negative-contrastive-learning-for-fine","slug":"hard-negative-contrastive-learning-for-fine","title":"Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models","date":"2025-05-26","arxiv_id":"2505.20152","n_code_links":1,"syntology":null},{"paper":"/paper/locality-aware-zero-shot-human-object","slug":"locality-aware-zero-shot-human-object","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","date":"2025-05-26","arxiv_id":"2505.19503","n_code_links":1,"syntology":null},{"paper":"/paper/one-surrogate-to-fool-them-all-universal","slug":"one-surrogate-to-fool-them-all-universal","title":"One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP","date":"2025-05-26","arxiv_id":"2505.19840","n_code_links":1,"syntology":null},{"paper":null,"slug":"stylear-customizing-multimodal-autoregressive","title":"StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation","date":"2025-05-26","arxiv_id":"2505.19874","n_code_links":0,"syntology":null},{"paper":null,"slug":"two-causally-related-needles-in-a-video","title":"Two Causally Related Needles in a Video Haystack","date":"2025-05-26","arxiv_id":"2505.19853","n_code_links":0,"syntology":null},{"paper":"/paper/amorlip-efficient-language-image-pretraining","slug":"amorlip-efficient-language-image-pretraining","title":"AmorLIP: Efficient Language-Image Pretraining via Amortization","date":"2025-05-25","arxiv_id":"2505.18983","n_code_links":1,"syntology":null},{"paper":null,"slug":"distill-clip-dclip-enhancing-image-text","title":"Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation","date":"2025-05-25","arxiv_id":"2505.21549","n_code_links":0,"syntology":null},{"paper":null,"slug":"docmmir-a-framework-for-document-multi-modal","title":"DocMMIR: A Framework for Document Multi-modal Information Retrieval","date":"2025-05-25","arxiv_id":"2505.19312","n_code_links":0,"syntology":null},{"paper":null,"slug":"ghostprompt-jailbreaking-text-to-image","title":"GhostPrompt: Jailbreaking Text-to-image Generative Models based on Dynamic Optimization","date":"2025-05-25","arxiv_id":"2505.18979","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":3094,"with_a_code_link":1617,"where_syntology_ran_a_sample":649,"not_listed_spam_title":0,"listed":3094,"listed_where_code_ran":649,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":525,"every_run_a_failure_of_syntologys_instrument":124,"listed_with_a_run_with_no_instrument_failure":525,"listed_every_run_a_failure_of_syntologys_instrument":124,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":649,"papers_where_code_ran_first_page":"/method/clip/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":31,"url":"/method/clip/papers/2","json":"/method/clip/papers/2.json","rows":100},{"order":"archive","page":3,"of":31,"url":"/method/clip/papers/3","json":"/method/clip/papers/3.json","rows":100},{"order":"archive","page":4,"of":31,"url":"/method/clip/papers/4","json":"/method/clip/papers/4.json","rows":100},{"order":"archive","page":5,"of":31,"url":"/method/clip/papers/5","json":"/method/clip/papers/5.json","rows":100},{"order":"archive","page":6,"of":31,"url":"/method/clip/papers/6","json":"/method/clip/papers/6.json","rows":100},{"order":"archive","page":7,"of":31,"url":"/method/clip/papers/7","json":"/method/clip/papers/7.json","rows":100},{"order":"archive","page":8,"of":31,"url":"/method/clip/papers/8","json":"/method/clip/papers/8.json","rows":100},{"order":"archive","page":9,"of":31,"url":"/method/clip/papers/9","json":"/method/clip/papers/9.json","rows":100},{"order":"archive","page":10,"of":31,"url":"/method/clip/papers/10","json":"/method/clip/papers/10.json","rows":100},{"order":"archive","page":11,"of":31,"url":"/method/clip/papers/11","json":"/method/clip/papers/11.json","rows":100},{"order":"archive","page":12,"of":31,"url":"/method/clip/papers/12","json":"/method/clip/papers/12.json","rows":100},{"order":"archive","page":13,"of":31,"url":"/method/clip/papers/13","json":"/method/clip/papers/13.json","rows":100},{"order":"archive","page":14,"of":31,"url":"/method/clip/papers/14","json":"/method/clip/papers/14.json","rows":100},{"order":"archive","page":15,"of":31,"url":"/method/clip/papers/15","json":"/method/clip/papers/15.json","rows":100},{"order":"archive","page":16,"of":31,"url":"/method/clip/papers/16","json":"/method/clip/papers/16.json","rows":100},{"order":"archive","page":17,"of":31,"url":"/method/clip/papers/17","json":"/method/clip/papers/17.json","rows":100},{"order":"archive","page":18,"of":31,"url":"/method/clip/papers/18","json":"/method/clip/papers/18.json","rows":100},{"order":"archive","page":19,"of":31,"url":"/method/clip/papers/19","json":"/method/clip/papers/19.json","rows":100},{"order":"archive","page":20,"of":31,"url":"/method/clip/papers/20","json":"/method/clip/papers/20.json","rows":100},{"order":"archive","page":21,"of":31,"url":"/method/clip/papers/21","json":"/method/clip/papers/21.json","rows":100},{"order":"archive","page":22,"of":31,"url":"/method/clip/papers/22","json":"/method/clip/papers/22.json","rows":100},{"order":"archive","page":23,"of":31,"url":"/method/clip/papers/23","json":"/method/clip/papers/23.json","rows":100},{"order":"archive","page":24,"of":31,"url":"/method/clip/papers/24","json":"/method/clip/papers/24.json","rows":100},{"order":"archive","page":25,"of":31,"url":"/method/clip/papers/25","json":"/method/clip/papers/25.json","rows":100},{"order":"archive","page":26,"of":31,"url":"/method/clip/papers/26","json":"/method/clip/papers/26.json","rows":100},{"order":"archive","page":27,"of":31,"url":"/method/clip/papers/27","json":"/method/clip/papers/27.json","rows":100},{"order":"archive","page":28,"of":31,"url":"/method/clip/papers/28","json":"/method/clip/papers/28.json","rows":100},{"order":"archive","page":29,"of":31,"url":"/method/clip/papers/29","json":"/method/clip/papers/29.json","rows":100},{"order":"archive","page":30,"of":31,"url":"/method/clip/papers/30","json":"/method/clip/papers/30.json","rows":100},{"order":"archive","page":31,"of":31,"url":"/method/clip/papers/31","json":"/method/clip/papers/31.json","rows":94},{"order":"ran","page":1,"of":7,"url":"/method/clip/papers/ran/1","json":"/method/clip/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":7,"url":"/method/clip/papers/ran/2","json":"/method/clip/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":7,"url":"/method/clip/papers/ran/3","json":"/method/clip/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":7,"url":"/method/clip/papers/ran/4","json":"/method/clip/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":7,"url":"/method/clip/papers/ran/5","json":"/method/clip/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":7,"url":"/method/clip/papers/ran/6","json":"/method/clip/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":7,"url":"/method/clip/papers/ran/7","json":"/method/clip/papers/ran/7.json","rows":49}],"tasks":[{"task":"/task/retrieval","name":"Retrieval","papers":336},{"task":"/task/language-modelling","name":"Language Modelling","papers":297},{"task":"/task/zero-shot-learning","name":"Zero-Shot Learning","papers":253},{"task":"/task/image-classification","name":"Image Classification","papers":250},{"task":"/task/image-generation","name":"Image Generation","papers":245},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":228},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":219},{"task":"/task/image-classification","name":"image-classification","papers":218},{"task":"/task/language-modeling","name":"Language Modeling","papers":193},{"task":"/task/prompt-learning","name":"Prompt Learning","papers":162},{"task":"/task/segmentation","name":"Segmentation","papers":161},{"task":null,"name":"zero-shot-classification","papers":158},{"task":"/task/representation-learning","name":"Representation Learning","papers":143},{"task":"/task/object","name":"Object","papers":142},{"task":"/task/image-captioning","name":"Image Captioning","papers":117},{"task":"/task/object-detection","name":"Object Detection","papers":117},{"task":"/task/object-detection-1","name":"object-detection","papers":115},{"task":"/task/text-to-image-generation","name":"Text-to-Image Generation","papers":109},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":107},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":106}],"tasks_shown":20,"n_tasks":947,"usage_by_year":[{"year":"2021","papers":101},{"year":"2022","papers":359},{"year":"2023","papers":887},{"year":"2024","papers":1191},{"year":"2025","papers":556}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/clip"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CLIP","read_at":"2026-10-05T00:53:44+00:00","query":"CLIP","kind":"paper","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2106.02524"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2103.00020","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"listed_only"},"retrieve_with":null,"name_competition":{"verdict":"outranked","may_be_wrong_sense":false,"bearers_found":3,"served":{"arxiv_id":"2106.02524","citations":27},"leading_other_bearer":{"arxiv_id":"2103.12531","title":"CLIP: Cheap Lipschitz Training of Neural Networks","citations":41,"named_by":["title_prefix"],"bearer_name":"CLIP: Cheap Lipschitz Training of Neural Networks","ask_with":"have('2103.12531')"},"n_other_bearers_listed":2,"note":"'CLIP' is ALSO the name of the paper 'CLIP: Cheap Lipschitz Training of Neural Networks' (arXiv:2103.12531, 41 citations), which is cited more than the paper this answer is about (27). The margin is narrow, so this is not a claim that the other one is what you meant -- check `served.arxiv_id` against the paper you had in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2106.02524","page":"/paper/clip-a-dataset-for-extracting-action-items","syntology_url":"https://syntology.ai/paper/2106.02524","in_graph_layer":false,"samples":0},"line":"about another paper, arXiv:2106.02524: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The lookup matched a paper by its title, arXiv:2106.02524, not a method entry. About another paper: this answer is about arXiv:2106.02524, while the archive credits arXiv:2103.00020.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"aaeabdfb41408c273398fd3cbb02489caab9c1b569a51a9e11232ac97af63f6c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}