{"total":186,"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"area":null},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165,"area":null},{"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":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","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":"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":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"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":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2402.01788","title":"LitLLM: A Toolkit for Scientific Literature Review","created":"2024-02-02","cited_by_count":63,"area":null},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49,"area":null},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47,"area":null},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44,"area":null},{"id":"2602.14486","title":"Revisiting the Platonic Representation Hypothesis: An Aristotelian View","created":"2026-02-16","cited_by_count":44,"area":null},{"id":"2411.02393","title":"Adaptive Length Image Tokenization via Recurrent Allocation","created":"2024-11-04","cited_by_count":43,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2112.09445","title":"Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation","created":"2021-12-17","cited_by_count":36,"area":null},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"id":"2502.16282","title":"Understanding the Emergence of Multimodal Representation Alignment","created":"2025-02-22","cited_by_count":31,"area":null},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30,"area":null},{"id":"2103.10480","title":"Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons","created":"2021-03-18","cited_by_count":29,"area":null},{"id":"2211.11248","title":"Video Background Music Generation: Dataset, Method and Evaluation","created":"2022-11-21","cited_by_count":29,"area":null},{"id":"2206.00100","title":"VALHALLA: Visual Hallucination for Machine Translation","created":"2022-05-31","cited_by_count":27,"area":null},{"id":"2310.07478","title":"Multimodal Graph Learning for Generative Tasks","created":"2023-10-11","cited_by_count":27,"area":null},{"id":"2311.12202","title":"Nepotistically Trained Generative-AI Models Collapse","created":"2023-11-20","cited_by_count":27,"area":null},{"id":"2406.04932","title":"Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networks","created":"2024-06-07","cited_by_count":27,"area":null},{"id":"2502.07870","title":"TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation","created":"2025-02-11","cited_by_count":27,"area":null},{"id":"2406.11030","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","created":"2024-06-16","cited_by_count":25,"area":null},{"id":"2206.00621","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","created":"2022-06-01","cited_by_count":24,"area":null},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23,"area":null},{"id":"2406.06393","title":"STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics","created":"2024-06-10","cited_by_count":23,"area":null},{"id":"2509.26625","title":"Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training","created":"2025-09-30","cited_by_count":23,"area":null},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","cited_by_count":20,"area":null},{"id":"2407.12616","title":"Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models","created":"2024-07-17","cited_by_count":20,"area":null},{"id":"2108.08688","title":"Contrastive Language-Image Pre-training for the Italian Language","created":"2021-08-19","cited_by_count":19,"area":null},{"id":"2401.08053","title":"SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation","created":"2024-01-16","cited_by_count":19,"area":null},{"id":"2210.01185","title":"ContraCLM: Contrastive Learning For Causal Language Model","created":"2022-10-03","cited_by_count":18,"area":null},{"id":"2305.03668","title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding","created":"2023-05-05","cited_by_count":18,"area":null},{"id":"2211.10780","title":"ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2302.13602","title":"The Role of Pre-training Data in Transfer Learning","created":"2023-02-27","cited_by_count":17,"area":null},{"id":"2410.17251","title":"Altogether: Image Captioning via Re-aligning Alt-text","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2510.16990","title":"Graph4MM: Weaving Multimodal Learning with Structural Information","created":"2025-10-19","cited_by_count":17,"area":null},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2210.13134","title":"Multilingual Multimodal Learning with Machine Translated Text","created":"2022-10-24","cited_by_count":16,"area":null},{"id":"2401.06659","title":"WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge","created":"2024-01-12","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2304.08480","title":"DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2308.15226","title":"CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation","created":"2023-08-29","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.24129","title":"It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2203.17273","title":"FindIt: Generalized Localization with Natural Language Queries","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2401.05736","title":"Cross-modal Retrieval for Knowledge-based Visual Question Answering","created":"2024-01-11","cited_by_count":13,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2203.14463","title":"Large-scale Bilingual Language-Image Contrastive Learning","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2410.07610","title":"CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features","created":"2024-10-10","cited_by_count":12,"area":null},{"id":"2503.01879","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2507.19054","title":"Closing the Modality Gap for Mixed Modality Search","created":"2025-07-25","cited_by_count":12,"area":null},{"id":"2306.08658","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","created":"2023-06-14","cited_by_count":11,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2411.17332","title":"On the Generalization of Handwritten Text Recognition Models","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2510.16641","title":"MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models","created":"2025-10-18","cited_by_count":10,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2305.17202","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2404.06119","title":"DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation","created":"2024-04-09","cited_by_count":9,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2202.07630","title":"Delving Deeper into Cross-lingual Visual Question Answering","created":"2022-02-15","cited_by_count":8,"area":null},{"id":"2305.05432","title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","created":"2023-05-09","cited_by_count":8,"area":null},{"id":"2402.15276","title":"CFIR: Fast and Effective Long-Text To Image Retrieval for Large Corpora","created":"2024-02-23","cited_by_count":8,"area":null},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2506.18372","title":"OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Grounding","created":"2025-06-23","cited_by_count":8,"area":null}],"next_cursor":"100"}