{"total":104,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187,"area":"distill"},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"area":"mllm"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2301.13155","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","created":"2023-01-30","cited_by_count":75,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2303.17561","title":"SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger","created":"2023-03-30","cited_by_count":56,"area":"mllm"},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48,"area":"mllm"},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2305.18287","title":"LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections","created":"2023-05-29","cited_by_count":43,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36,"area":null},{"id":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2310.00927","title":"Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP","created":"2023-10-02","cited_by_count":26,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2404.04936","title":"Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models","created":"2024-04-07","cited_by_count":24,"area":null},{"id":"2206.11134","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","created":"2022-06-22","cited_by_count":23,"area":null},{"id":"2212.08653","title":"Attentive Mask CLIP","created":"2022-12-16","cited_by_count":23,"area":null},{"id":"2302.14057","title":"Cross-modal Contrastive Learning for Multimodal Fake News Detection","created":"2023-02-25","cited_by_count":23,"area":null},{"id":"2310.07355","title":"IMITATE: Clinical Prior Guided Hierarchical Vision-Language Pre-training","created":"2023-10-11","cited_by_count":23,"area":"mllm"},{"id":"2504.01916","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","created":"2025-04-02","cited_by_count":23,"area":"mllm"},{"id":"2209.02700","title":"Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification","created":"2022-09-06","cited_by_count":20,"area":null},{"id":"2211.09790","title":"ConStruct-VL: Data-Free Continual Structured VL Concepts Learning","created":"2022-11-17","cited_by_count":20,"area":null},{"id":"2305.08675","title":"Improved baselines for vision-language pre-training","created":"2023-05-15","cited_by_count":20,"area":"mllm"},{"id":"2208.13628","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","created":"2022-08-29","cited_by_count":19,"area":"mllm"},{"id":"2312.04554","title":"Improved Visual Grounding through Self-Consistent Explanations","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2312.01522","title":"G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training","created":"2023-12-03","cited_by_count":12,"area":"mllm"},{"id":"2405.06784","title":"Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare","created":"2024-05-10","cited_by_count":12,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2404.03323","title":"Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2409.07967","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","created":"2024-09-12","cited_by_count":11,"area":null},{"id":"2312.12661","title":"Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining","created":"2023-12-19","cited_by_count":10,"area":null},{"id":"2405.15668","title":"What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models","created":"2024-05-24","cited_by_count":10,"area":"mllm"},{"id":"2505.22079","title":"Bringing CLIP to the Clinic: Dynamic Soft Labels and Negation-Aware Learning for Medical Analysis","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2403.18260","title":"Toward Interactive Regional Understanding in Vision-Large Language Models","created":"2024-03-27","cited_by_count":9,"area":"mllm"},{"id":"2404.09387","title":"RankCLIP: Ranking-Consistent Language-Image Pretraining","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2408.04145","title":"ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model","created":"2024-08-08","cited_by_count":9,"area":"distill"},{"id":"2309.06809","title":"TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2405.17201","title":"Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View","created":"2024-05-27","cited_by_count":7,"area":"lr"},{"id":"2305.14281","title":"Weakly-Supervised Learning of Visual Relations in Multimodal Pretraining","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2406.01460","title":"MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2407.14007","title":"Multi-modal Relation Distillation for Unified 3D Representation Learning","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2407.14117","title":"Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation","created":"2024-07-19","cited_by_count":5,"area":"mllm"},{"id":"2501.04579","title":"Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2509.25202","title":"VLHSA: Vision-Language Hierarchical Semantic Alignment for Jigsaw Puzzle Solving with Eroded Gaps","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2512.14480","title":"SuperCLIP: CLIP with Simple Classification Supervision","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2312.00674","title":"LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models","created":"2023-12-01","cited_by_count":3,"area":"mllm"},{"id":"2405.09922","title":"Cross-sensor self-supervised training and alignment for remote sensing","created":"2024-05-16","cited_by_count":3,"area":null},{"id":"2407.12880","title":"Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detection","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2412.16576","title":"Open-Vocabulary Mobile Manipulation Based on Double Relaxed Contrastive Learning with Dense Labeling","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.04666","title":"What Are You Doing? A Closer Look at Controllable Human Video Generation","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2504.19627","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning","created":"2025-04-28","cited_by_count":3,"area":"lr"},{"id":"2509.18717","title":"Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment","created":"2025-09-23","cited_by_count":3,"area":"safety"},{"id":"2511.15633","title":"Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2401.06969","title":"Domain Adaptation for Large-Vocabulary Object Detectors","created":"2024-01-13","cited_by_count":2,"area":null},{"id":"2409.17777","title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2502.00618","title":"DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition","created":"2025-02-02","cited_by_count":2,"area":"mllm"},{"id":"2503.06626","title":"DiffCLIP: Differential Attention Meets CLIP","created":"2025-03-09","cited_by_count":2,"area":"mllm"},{"id":"2503.19801","title":"SeLIP: Similarity Enhanced Contrastive Language Image Pretraining for Multi-modal Head MRI","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2511.17103","title":"Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2512.11141","title":"Learning complete and explainable visual representations from itemized text supervision","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2306.00813","title":"UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning","created":"2023-06-01","cited_by_count":1,"area":"mllm"},{"id":"2409.08206","title":"ComAlign: Compositional Alignment in Vision-Language Models","created":"2024-09-12","cited_by_count":1,"area":"mllm"},{"id":"2503.23534","title":"BiPVL-Seg: Bidirectional Progressive Vision-Language Fusion with Global-Local Alignment for Medical Image Segmentation","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2505.07675","title":"Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization","created":"2025-05-12","cited_by_count":1,"area":"mllm"},{"id":"2506.09691","title":"Adding simple structure at inference improves Vision-Language Compositionality","created":"2025-06-11","cited_by_count":1,"area":"mllm"},{"id":"2506.23502","title":"LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching","created":"2025-06-30","cited_by_count":1,"area":"mllm"},{"id":"2507.03434","title":"Unlearning the Noisy Correspondence Makes CLIP More Robust","created":"2025-07-04","cited_by_count":1,"area":"mllm"},{"id":"2508.04136","title":"UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval","created":"2025-08-06","cited_by_count":1,"area":"mllm"},{"id":"2508.17497","title":"Multimodal Representation Learning Conditioned on Semantic Relations","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2602.21175","title":"Seeing Through Words: Controlling Visual Retrieval Quality with Language Models","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.11496","title":"Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.12391","title":"Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.06229","title":"Look Beyond Saliency: Low-Attention Guided Dual Encoding for Video Semantic Search","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2608.07993","title":"MRBench: A Comprehensive Benchmark for Human Motion-Text Retrieval","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2403.06136","title":"RESTORE: Towards Feature Shift for Vision-Language Prompt Learning","created":"2024-03-10","cited_by_count":0,"area":null},{"id":"2406.11252","title":"Mining Open Semantics from CLIP: A Relation Transition Perspective for Few-Shot Learning","created":"2024-06-17","cited_by_count":0,"area":"mllm"},{"id":"2502.18047","title":"Progressive Local Alignment for Medical Multimodal Pre-training","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2509.08570","title":"Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2511.20274","title":"SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.02566","title":"From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature","created":"2025-12-02","cited_by_count":0,"area":"mllm"},{"id":"2601.13622","title":"CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models","created":"2026-01-20","cited_by_count":0,"area":"mllm"},{"id":"2603.05446","title":"NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries","created":"2026-03-05","cited_by_count":0,"area":null}],"next_cursor":"100"}