{"total":226,"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711,"area":null},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"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":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"area":"lr"},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329,"area":"mllm"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219,"area":null},{"id":"2308.02487","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","created":"2023-08-04","cited_by_count":201,"area":null},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194,"area":null},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179,"area":null},{"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":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171,"area":null},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170,"area":"mllm"},{"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":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2204.02849","title":"KNN-Diffusion: Image Generation via Large-Scale Retrieval","created":"2022-04-06","cited_by_count":137,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128,"area":null},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127,"area":"lr"},{"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":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2308.06595","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","created":"2023-08-12","cited_by_count":102,"area":"mllm"},{"id":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100,"area":null},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99,"area":null},{"id":"2311.15537","title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","created":"2023-11-27","cited_by_count":97,"area":null},{"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":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87,"area":"mllm"},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86,"area":null},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86,"area":null},{"id":"2112.05253","title":"MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning","created":"2021-12-09","cited_by_count":85,"area":null},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70,"area":null},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70,"area":"mllm"},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64,"area":null},{"id":"2111.12872","title":"Less is More: Generating Grounded Navigation Instructions from Landmarks","created":"2021-11-25","cited_by_count":64,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2110.10834","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","created":"2021-10-21","cited_by_count":52,"area":null},{"id":"2306.00637","title":"Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models","created":"2023-06-01","cited_by_count":51,"area":"diffusion"},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"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":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43,"area":"mllm"},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43,"area":null},{"id":"2301.09506","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","created":"2023-01-23","cited_by_count":43,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2211.12112","title":"Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark","created":"2022-11-22","cited_by_count":41,"area":null},{"id":"2304.01198","title":"Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network","created":"2023-04-03","cited_by_count":40,"area":null},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39,"area":null},{"id":"2211.15388","title":"Shifted Diffusion for Text-to-image Generation","created":"2022-11-24","cited_by_count":37,"area":"diffusion"},{"id":"2407.06438","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling","created":"2024-07-08","cited_by_count":37,"area":"mllm"},{"id":"2204.07660","title":"It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection","created":"2022-04-15","cited_by_count":36,"area":null},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35,"area":"mllm"},{"id":"2406.09829","title":"Open-Vocabulary Semantic Segmentation with Image Embedding Balancing","created":"2024-06-14","cited_by_count":35,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2405.15232","title":"DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception","created":"2024-05-24","cited_by_count":32,"area":"mllm"},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30,"area":null},{"id":"2208.03354","title":"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch","created":"2022-08-05","cited_by_count":28,"area":null},{"id":"2401.09454","title":"Voila-A: Aligning Vision-Language Models with User's Gaze Attention","created":"2023-12-22","cited_by_count":28,"area":"mllm"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27,"area":null},{"id":"2305.13631","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2404.06214","title":"[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus","created":"2024-04-09","cited_by_count":26,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2308.06412","title":"Taming Self-Training for Open-Vocabulary Object Detection","created":"2023-08-11","cited_by_count":25,"area":"synth"},{"id":"2506.10128","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs","created":"2025-06-11","cited_by_count":25,"area":"lr"},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2502.10645","title":"BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop","created":"2025-02-15","cited_by_count":24,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2210.14142","title":"From colouring-in to pointillism: revisiting semantic segmentation supervision","created":"2022-10-25","cited_by_count":22,"area":null},{"id":"2305.09073","title":"Consensus and Subjectivity of Skin Tone Annotation for ML Fairness","created":"2023-05-16","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2107.00249","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","created":"2021-07-01","cited_by_count":20,"area":null},{"id":"2305.19075","title":"Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data","created":"2023-05-30","cited_by_count":20,"area":"offlinerl"},{"id":"2104.01894","title":"Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval","created":"2021-04-05","cited_by_count":19,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2312.09237","title":"Pixel Aligned Language Models","created":"2023-12-14","cited_by_count":17,"area":"mllm"},{"id":"2411.14723","title":"Effective SAM Combination for Open-Vocabulary Semantic Segmentation","created":"2024-11-22","cited_by_count":17,"area":null}],"next_cursor":"100"}