{"total":55,"rows":[{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115,"area":"safety"},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2305.13653","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2209.15266","title":"Data Poisoning Attacks Against Multimodal Encoders","created":"2022-09-30","cited_by_count":41,"area":"safety"},{"id":"2312.04403","title":"OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimization","created":"2023-12-07","cited_by_count":37,"area":"mllm"},{"id":"2405.16148","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","created":"2024-05-25","cited_by_count":35,"area":"inference"},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20,"area":null},{"id":"2305.12964","title":"Text-based Person Search without Parallel Image-Text Data","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","cited_by_count":17,"area":null},{"id":"2308.12636","title":"Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learning","created":"2023-08-24","cited_by_count":16,"area":"mllm"},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12,"area":null},{"id":"2504.08851","title":"Mimic In-Context Learning for Multimodal Tasks","created":"2025-04-11","cited_by_count":12,"area":"mllm"},{"id":"2401.01065","title":"BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving","created":"2024-01-02","cited_by_count":11,"area":"driving"},{"id":"2411.12195","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","created":"2024-11-19","cited_by_count":11,"area":null},{"id":"2408.01228","title":"The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models","created":"2024-08-02","cited_by_count":8,"area":"mllm"},{"id":"2510.17847","title":"CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","created":"2025-10-11","cited_by_count":8,"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"},{"id":"2403.10883","title":"Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction","created":"2024-03-16","cited_by_count":7,"area":"mllm"},{"id":"2510.14824","title":"Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking","created":"2025-10-16","cited_by_count":6,"area":"mllm"},{"id":"2603.04772","title":"TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings","created":"2026-03-05","cited_by_count":6,"area":"lr"},{"id":"2305.01788","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2403.00284","title":"A Survey of Route Recommendations: Methods, Applications, and Opportunities","created":"2024-03-01","cited_by_count":5,"area":null},{"id":"2407.15239","title":"Benchmark Granularity and Model Robustness for Image-Text Retrieval","created":"2024-07-21","cited_by_count":5,"area":"mllm"},{"id":"2305.04497","title":"IIITD-20K: Dense captioning for Text-Image ReID","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2404.18106","title":"Semi-supervised Text-based Person Search","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2505.02549","title":"Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2505.11029","title":"Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere","created":"2025-05-16","cited_by_count":4,"area":"mllm"},{"id":"2407.12346","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","created":"2024-07-17","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":"2303.00181","title":"Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2305.03510","title":"Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2308.11994","title":"Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrieval","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2407.05980","title":"MMIS: Multimodal Dataset for Interior Scene Visual Generation and Recognition","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2412.10353","title":"Robust image classification with multi-modal large language models","created":"2024-12-13","cited_by_count":2,"area":"mllm"},{"id":"2501.13851","title":"Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes","created":"2025-01-23","cited_by_count":2,"area":"mllm"},{"id":"2507.06654","title":"MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2309.03100","title":"FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2506.09691","title":"Adding simple structure at inference improves Vision-Language Compositionality","created":"2025-06-11","cited_by_count":1,"area":"mllm"},{"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":"2608.06901","title":"Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models","created":"2026-08-07","cited_by_count":1,"area":"mllm"},{"id":"2208.09198","title":"Test-time Training for Data-efficient UCDR","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2303.07740","title":"Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening","created":"2023-03-14","cited_by_count":0,"area":null},{"id":"2405.11496","title":"DEMO: A Statistical Perspective for Efficient Image-Text Matching","created":"2024-05-19","cited_by_count":0,"area":null},{"id":"2411.18727","title":"Generative Visual Communication in the Era of Vision-Language Models","created":"2024-11-27","cited_by_count":0,"area":"mllm"},{"id":"2502.11205","title":"Deep Contrastive Learning for Feature Alignment: Insights from Housing-Household Relationship Inference","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2503.07456","title":"Anatomy-Aware Conditional Image-Text Retrieval","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2510.02913","title":"Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting","created":"2025-10-03","cited_by_count":0,"area":"mllm"},{"id":"2510.07058","title":"Concept Retrieval -- What and How?","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.22783","title":"Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.16499","title":"HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2608.24010","title":"Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.12965","title":"Generative Retrieval for Unsupervised Text-Based Person Search","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}