{"total":101,"rows":[{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103,"area":null},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65,"area":null},{"id":"2311.16494","title":"ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models","created":"2023-11-27","cited_by_count":39,"area":"mllm"},{"id":"2401.02418","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","created":"2024-01-04","cited_by_count":38,"area":"mllm"},{"id":"2406.02915","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","created":"2024-06-05","cited_by_count":30,"area":"mllm"},{"id":"2403.11755","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","created":"2024-03-18","cited_by_count":29,"area":"mllm"},{"id":"2404.04072","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","created":"2024-04-05","cited_by_count":28,"area":"mllm"},{"id":"2407.04603","title":"AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation","created":"2024-07-05","cited_by_count":28,"area":"mllm"},{"id":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25,"area":null},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2402.10099","title":"Any-Shift Prompting for Generalization over Distributions","created":"2024-02-15","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","cited_by_count":17,"area":"mllm"},{"id":"2412.11576","title":"DCBM: Data-Efficient Visual Concept Bottleneck Models","created":"2024-12-16","cited_by_count":16,"area":null},{"id":"2510.24038","title":"Enhancing CLIP Robustness via Cross-Modality Alignment","created":"2025-10-28","cited_by_count":15,"area":"mllm"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"id":"2311.07593","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","created":"2023-11-10","cited_by_count":13,"area":"mllm"},{"id":"2502.19844","title":"ProAPO: Progressively Automatic Prompt Optimization for Visual Classification","created":"2025-02-27","cited_by_count":13,"area":"mllm"},{"id":"2410.14690","title":"Rethinking VLMs and LLMs for Image Classification","created":"2024-10-03","cited_by_count":12,"area":"lr"},{"id":"2311.11904","title":"LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual Descriptions","created":"2023-11-20","cited_by_count":11,"area":"mllm"},{"id":"2405.10053","title":"SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection","created":"2024-05-16","cited_by_count":11,"area":null},{"id":"2408.05775","title":"Efficient Test-Time Prompt Tuning for Vision-Language Models","created":"2024-08-11","cited_by_count":10,"area":"mllm"},{"id":"2503.18623","title":"Training-Free Personalization via Retrieval and Reasoning on Fingerprints","created":"2025-03-24","cited_by_count":10,"area":"lr"},{"id":"2505.14462","title":"RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2404.00701","title":"Training-Free Semantic Segmentation via LLM-Supervision","created":"2024-03-31","cited_by_count":8,"area":null},{"id":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2403.05297","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2410.11201","title":"Tree of Attributes Prompt Learning for Vision-Language Models","created":"2024-10-15","cited_by_count":7,"area":"mllm"},{"id":"2412.08536","title":"SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting","created":"2024-12-11","cited_by_count":7,"area":"mllm"},{"id":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"id":"2311.13612","title":"Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2408.16412","title":"Text-Enhanced Zero-Shot Action Recognition: A training-free approach","created":"2024-08-29","cited_by_count":6,"area":"mllm"},{"id":"2410.06154","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","created":"2024-10-08","cited_by_count":6,"area":"mllm"},{"id":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2412.11375","title":"Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2412.11917","title":"Does VLM Classification Benefit from LLM Description Semantics?","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2506.23822","title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","created":"2025-06-30","cited_by_count":6,"area":"mllm"},{"id":"2310.15324","title":"Videoprompter: an ensemble of foundational models for zero-shot video understanding","created":"2023-10-23","cited_by_count":5,"area":"mllm"},{"id":"2311.11293","title":"From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2405.03243","title":"Mind the Gap Between Synthetic and Real: Utilizing Transfer Learning to Probe the Boundaries of Stable Diffusion Generated Data","created":"2024-05-06","cited_by_count":5,"area":"diffusion"},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5,"area":"mllm"},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2505.13233","title":"From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection","created":"2025-05-19","cited_by_count":5,"area":"mllm"},{"id":"2509.19994","title":"Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2407.15613","title":"Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2501.01109","title":"BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization","created":"2025-01-02","cited_by_count":4,"area":null},{"id":"2504.10487","title":"FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation","created":"2025-04-14","cited_by_count":4,"area":null},{"id":"2506.05146","title":"CIVET: Systematic Evaluation of Understanding in VLMs","created":"2025-06-05","cited_by_count":4,"area":"mllm"},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2402.04416","title":"Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2409.13676","title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2410.08211","title":"LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts","created":"2024-10-10","cited_by_count":3,"area":"mllm"},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2412.13947","title":"Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition","created":"2024-12-18","cited_by_count":3,"area":"mllm"},{"id":"2503.19145","title":"Compositional Caching for Training-free Open-vocabulary Attribute Detection","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2309.16414","title":"AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models","created":"2023-09-28","cited_by_count":2,"area":"mllm"},{"id":"2404.16717","title":"Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class","created":"2024-04-25","cited_by_count":2,"area":"mllm"},{"id":"2407.05061","title":"Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models","created":"2024-07-06","cited_by_count":2,"area":"mllm"},{"id":"2411.05357","title":"Enhancing Visual Classification using Comparative Descriptors","created":"2024-11-08","cited_by_count":2,"area":"mllm"},{"id":"2502.16911","title":"SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models","created":"2025-02-24","cited_by_count":2,"area":"mllm"},{"id":"2503.05424","title":"Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2505.23704","title":"CLDTracker: A Comprehensive Language Description for Visual Tracking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.03803","title":"Causality-guided Prompt Learning for Vision-language Models via Visual Granulation","created":"2025-09-04","cited_by_count":2,"area":"mllm"},{"id":"2511.18305","title":"DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition","created":"2025-11-23","cited_by_count":2,"area":"lr"},{"id":"2605.12325","title":"VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2405.02586","title":"Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis","created":"2024-05-04","cited_by_count":1,"area":"mllm"},{"id":"2407.15731","title":"The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models","created":"2024-07-22","cited_by_count":1,"area":"mllm"},{"id":"2412.00364","title":"LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2507.23070","title":"Vocabulary-free Fine-grained Visual Recognition via Enriched Contextually Grounded Vision-Language Model","created":"2025-07-30","cited_by_count":1,"area":"mllm"},{"id":"2508.11919","title":"TimeSenCLIP: A Time Series Vision-Language Model for Remote Sensing","created":"2025-08-16","cited_by_count":1,"area":"mllm"},{"id":"2508.17417","title":"Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models","created":"2025-08-24","cited_by_count":1,"area":"mllm"},{"id":"2509.13676","title":"Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation","created":"2025-09-17","cited_by_count":1,"area":"mllm"},{"id":"2601.10835","title":"Can Vision-Language Models Understand Construction Workers? An Exploratory Study","created":"2026-01-15","cited_by_count":1,"area":"mllm"},{"id":"2601.20419","title":"Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models","created":"2026-01-28","cited_by_count":1,"area":"mllm"},{"id":"2411.16236","title":"DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2503.10731","title":"Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2507.03458","title":"Helping CLIP See Both the Forest and the Trees: A Decomposition and Description Approach","created":"2025-07-04","cited_by_count":0,"area":"mllm"},{"id":"2507.03542","title":"Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor","created":"2025-07-04","cited_by_count":0,"area":"mllm"},{"id":"2507.07147","title":"Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation","created":"2025-07-09","cited_by_count":0,"area":"mllm"},{"id":"2508.16313","title":"Retrieval Enhanced Feedback via In-context Neural Error-book","created":"2025-08-22","cited_by_count":0,"area":"lr"},{"id":"2509.12771","title":"Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.17522","title":"Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.00419","title":"LGCA: Enhancing Semantic Representation via Progressive Expansion","created":"2025-11-01","cited_by_count":0,"area":"mllm"},{"id":"2511.00480","title":"FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts","created":"2025-11-01","cited_by_count":0,"area":"mllm"},{"id":"2512.18411","title":"AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning","created":"2025-12-20","cited_by_count":0,"area":"mllm"},{"id":"2601.21426","title":"MultiModal Fine-tuning with Synthetic Captions","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.26798","title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2604.01361","title":"IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.15622","title":"AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.04504","title":"SpecPL: Disentangling Spectral Granularity for Prompt Learning","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.08156","title":"LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2607.00684","title":"AdaBoosting Text Prompts for Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.18695","title":"Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2608.26744","title":"G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}