{"total":201,"rows":[{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386,"area":"mllm"},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224,"area":"mllm"},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336,"area":"mllm"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263,"area":"mllm"},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2310.16045","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","created":"2023-10-24","cited_by_count":226,"area":"mllm"},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109,"area":"mllm"},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"area":"mllm"},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70,"area":"mllm"},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2311.16194","title":"BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP","created":"2023-11-26","cited_by_count":67,"area":"mllm"},{"id":"2310.13355","title":"SILC: Improving Vision Language Pretraining with Self-Distillation","created":"2023-10-20","cited_by_count":66,"area":"mllm"},{"id":"2306.11925","title":"LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching","created":"2023-06-20","cited_by_count":60,"area":"mllm"},{"id":"2401.02460","title":"Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions","created":"2024-01-04","cited_by_count":54,"area":"mllm"},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2312.00825","title":"SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples","created":"2023-11-30","cited_by_count":53,"area":"mllm"},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2306.12424","title":"VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution","created":"2023-06-21","cited_by_count":52,"area":"mllm"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"area":"mllm"},{"id":"2305.17455","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","created":"2023-05-27","cited_by_count":44,"area":"mllm"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2310.08255","title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","created":"2023-10-12","cited_by_count":41,"area":"mllm"},{"id":"2206.01127","title":"VL-BEiT: Generative Vision-Language Pretraining","created":"2022-06-02","cited_by_count":39,"area":"mllm"},{"id":"2303.02483","title":"FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks","created":"2023-03-04","cited_by_count":38,"area":"mllm"},{"id":"2309.05950","title":"Language Models as Black-Box Optimizers for Vision-Language Models","created":"2023-09-12","cited_by_count":36,"area":"mllm"},{"id":"2405.18330","title":"Frustratingly Easy Test-Time Adaptation of Vision-Language Models","created":"2024-05-28","cited_by_count":36,"area":"mllm"},{"id":"2303.14865","title":"Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens","created":"2023-03-27","cited_by_count":35,"area":"mllm"},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35,"area":"mllm"},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35,"area":"mllm"},{"id":"2310.00647","title":"Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning","created":"2023-10-01","cited_by_count":30,"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":"2501.02430","title":"FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance","created":"2025-01-05","cited_by_count":30,"area":"mllm"},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28,"area":"mllm"},{"id":"2308.07706","title":"Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Models","created":"2023-08-15","cited_by_count":28,"area":"mllm"},{"id":"2412.00832","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","created":"2024-12-01","cited_by_count":28,"area":"mllm"},{"id":"2301.02241","title":"CiT: Curation in Training for Effective Vision-Language Data","created":"2023-01-05","cited_by_count":27,"area":"mllm"},{"id":"2404.00851","title":"Prompt Learning via Meta-Regularization","created":"2024-04-01","cited_by_count":26,"area":"mllm"},{"id":"2403.15593","title":"FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs","created":"2024-03-22","cited_by_count":25,"area":"mllm"},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2205.03860","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","created":"2022-05-08","cited_by_count":21,"area":"mllm"},{"id":"2308.12898","title":"Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?","created":"2023-08-24","cited_by_count":21,"area":"mllm"},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","cited_by_count":20,"area":"mllm"},{"id":"2305.08675","title":"Improved baselines for vision-language pre-training","created":"2023-05-15","cited_by_count":20,"area":"mllm"},{"id":"2312.02021","title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","created":"2023-12-04","cited_by_count":20,"area":"mllm"},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","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":"2406.09250","title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","created":"2024-06-13","cited_by_count":19,"area":"mllm"},{"id":"2508.04227","title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","created":"2025-08-06","cited_by_count":18,"area":"mllm"},{"id":"2206.07699","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","created":"2022-06-15","cited_by_count":17,"area":"mllm"},{"id":"2304.03659","title":"Probing Conceptual Understanding of Large Visual-Language Models","created":"2023-04-07","cited_by_count":17,"area":"mllm"},{"id":"2306.10159","title":"Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos","created":"2023-06-16","cited_by_count":17,"area":"mllm"},{"id":"2312.08878","title":"Domain Prompt Learning with Quaternion Networks","created":"2023-12-12","cited_by_count":17,"area":"mllm"},{"id":"2404.14715","title":"FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction","created":"2024-04-23","cited_by_count":17,"area":"mllm"},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17,"area":"mllm"},{"id":"2203.14395","title":"Single-Stream Multi-Level Alignment for Vision-Language Pretraining","created":"2022-03-27","cited_by_count":16,"area":"mllm"},{"id":"2504.03254","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","created":"2025-04-04","cited_by_count":16,"area":"mllm"},{"id":"2504.21051","title":"Multimodal Large Language Models for Medicine: A Comprehensive Survey","created":"2025-04-29","cited_by_count":16,"area":"mllm"},{"id":"2303.09252","title":"GridCLIP: One-Stage Object Detection by Grid-Level CLIP Representation Learning","created":"2023-03-16","cited_by_count":15,"area":"mllm"},{"id":"2311.17095","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","created":"2023-11-28","cited_by_count":15,"area":"mllm"},{"id":"2410.03176","title":"Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models","created":"2024-10-04","cited_by_count":15,"area":"mllm"},{"id":"2410.22187","title":"Active Learning for Vision-Language Models","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14,"area":"mllm"},{"id":"2404.16804","title":"AAPL: Adding Attributes to Prompt Learning for Vision-Language Models","created":"2024-04-25","cited_by_count":14,"area":"mllm"},{"id":"2407.00263","title":"From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models","created":"2024-06-28","cited_by_count":14,"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":"2502.11073","title":"Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2208.13474","title":"Prompt Tuning with Soft Context Sharing for Vision-Language Models","created":"2022-08-29","cited_by_count":13,"area":"mllm"},{"id":"2210.04506","title":"Bridging CLIP and StyleGAN through Latent Alignment for Image Editing","created":"2022-10-10","cited_by_count":12,"area":"mllm"},{"id":"2403.00219","title":"Multi-modal Attribute Prompting for Vision-Language Models","created":"2024-03-01","cited_by_count":12,"area":"mllm"},{"id":"2503.10166","title":"ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning","created":"2025-03-13","cited_by_count":12,"area":"mllm"},{"id":"2404.06244","title":"Anchor-based Robust Finetuning of Vision-Language Models","created":"2024-04-09","cited_by_count":11,"area":"mllm"},{"id":"2308.03151","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","created":"2023-08-06","cited_by_count":10,"area":"mllm"},{"id":"2504.09480","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","created":"2025-04-13","cited_by_count":10,"area":"mllm"},{"id":"2211.15398","title":"Leveraging per Image-Token Consistency for Vision-Language Pre-training","created":"2022-11-20","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":"2505.05163","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","created":"2025-05-08","cited_by_count":9,"area":"mllm"},{"id":"2209.15270","title":"ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training","created":"2022-09-30","cited_by_count":8,"area":"mllm"},{"id":"2212.04412","title":"Task Bias in Vision-Language Models","created":"2022-12-08","cited_by_count":8,"area":"mllm"},{"id":"2403.08271","title":"Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification","created":"2024-03-13","cited_by_count":8,"area":"mllm"},{"id":"2404.10864","title":"Vocabulary-free Image Classification and Semantic Segmentation","created":"2024-04-16","cited_by_count":8,"area":"mllm"},{"id":"2409.09502","title":"One missing piece in Vision and Language: A Survey on Comics Understanding","created":"2024-09-14","cited_by_count":8,"area":"mllm"},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8,"area":"mllm"},{"id":"2511.04727","title":"IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs","created":"2025-11-06","cited_by_count":8,"area":"mllm"},{"id":"2211.04861","title":"ERNIE-UniX2: A Unified Cross-lingual Cross-modal Framework for Understanding and Generation","created":"2022-11-09","cited_by_count":7,"area":"mllm"},{"id":"2211.16504","title":"Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles","created":"2022-11-29","cited_by_count":7,"area":"mllm"}],"next_cursor":"100"}