{"total":51,"rows":[{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196,"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":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2104.02096","title":"Compressing Visual-linguistic Model via Knowledge Distillation","created":"2021-04-05","cited_by_count":86,"area":"distill"},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"area":"mllm"},{"id":"2210.07795","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","created":"2022-10-14","cited_by_count":56,"area":"mllm"},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2305.17530","title":"PuMer: Pruning and Merging Tokens for Efficient Vision Language Models","created":"2023-05-27","cited_by_count":53,"area":"mllm"},{"id":"2111.10023","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","created":"2021-11-19","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"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":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2502.07855","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","created":"2025-02-11","cited_by_count":29,"area":"mllm"},{"id":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2305.04474","title":"TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2404.09275","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","created":"2024-04-14","cited_by_count":17,"area":"mllm"},{"id":"2211.11694","title":"Exploring Discrete Diffusion Models for Image Captioning","created":"2022-11-21","cited_by_count":16,"area":"diffusion"},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"area":null},{"id":"2212.08985","title":"Efficient Image Captioning for Edge Devices","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2201.12723","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","created":"2022-01-30","cited_by_count":12,"area":null},{"id":"2310.04550","title":"Module-wise Adaptive Distillation for Multimodality Foundation Models","created":"2023-10-06","cited_by_count":12,"area":null},{"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":"2203.05465","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","created":"2022-03-10","cited_by_count":9,"area":null},{"id":"2109.07301","title":"What Vision-Language Models `See' when they See Scenes","created":"2021-09-15","cited_by_count":8,"area":"mllm"},{"id":"2305.15033","title":"SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models","created":"2023-05-24","cited_by_count":7,"area":"mllm"},{"id":"2307.10188","title":"Several categories of Large Language Models (LLMs): A Short Survey","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2507.10844","title":"LLM-Guided Agentic Object Detection for Open-World Understanding","created":"2025-07-14","cited_by_count":7,"area":"agents"},{"id":"2307.08504","title":"BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization","created":"2023-07-17","cited_by_count":5,"area":"mllm"},{"id":"2308.03475","title":"COPA: Efficient Vision-Language Pre-training Through Collaborative Object- and Patch-Text Alignment","created":"2023-08-07","cited_by_count":5,"area":"mllm"},{"id":"2308.12956","title":"DLIP: Distilling Language-Image Pre-training","created":"2023-08-24","cited_by_count":5,"area":"mllm"},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2510.14896","title":"Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection","created":"2025-10-16","cited_by_count":4,"area":"mllm"},{"id":"2312.08846","title":"TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training","created":"2023-12-14","cited_by_count":3,"area":"mllm"},{"id":"2401.11633","title":"Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss","created":"2024-01-22","cited_by_count":3,"area":"mllm"},{"id":"2503.05143","title":"FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data","created":"2025-03-07","cited_by_count":3,"area":"agents"},{"id":"2202.07712","title":"Privacy Preserving Visual Question Answering","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2408.13963","title":"Shifted Window Fourier Transform And Retention For Image Captioning","created":"2024-08-25","cited_by_count":2,"area":null},{"id":"2505.11535","title":"Bridging Human Oversight and Black-box Driver Assistance: Vision-Language Models for Predictive Alerting in Lane Keeping Assist Systems","created":"2025-05-14","cited_by_count":2,"area":"mllm"},{"id":"2602.04071","title":"Agentic AI-Empowered Dynamic Survey Framework","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2403.07883","title":"Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2604.03172","title":"EffiMiniVLM: A Compact Dual-Encoder Regression Framework","created":"2026-04-03","cited_by_count":1,"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":"2307.05591","title":"Linear Alignment of Vision-language Models for Image Captioning","created":"2023-07-10","cited_by_count":0,"area":"mllm"},{"id":"2311.17267","title":"E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2604.18452","title":"ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting","created":"2026-04-20","cited_by_count":0,"area":"mllm"},{"id":"2609.28757","title":"Small yet Assistive: Spatially-Aware Post-Training for Low Vision","created":"2026-09-23","cited_by_count":0,"area":"mllm"}],"next_cursor":null}