{"total":287,"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":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"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":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647,"area":"mllm"},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"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":"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":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445,"area":"mllm"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"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":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"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":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196,"area":"mllm"},{"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":"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":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165,"area":null},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163,"area":"diffusion"},{"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":"2306.11300","title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","created":"2023-06-20","cited_by_count":151,"area":"mllm"},{"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":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"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":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123,"area":"mllm"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"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":"2202.06767","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","created":"2022-02-14","cited_by_count":114,"area":"mllm"},{"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":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"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":"2406.11833","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","created":"2024-06-17","cited_by_count":90,"area":"mllm"},{"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":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83,"area":"diffusion"},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"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":"2308.14960","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","created":"2023-08-29","cited_by_count":58,"area":"mllm"},{"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":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"id":"2509.03498","title":"OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation","created":"2025-09-03","cited_by_count":50,"area":"moe"},{"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":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"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":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42,"area":"mllm"},{"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":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35,"area":"mllm"},{"id":"2312.08207","title":"Black-box Membership Inference Attacks against Fine-tuned Diffusion Models","created":"2023-12-13","cited_by_count":35,"area":"diffusion"},{"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":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"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":"2308.09991","title":"AltDiffusion: A Multilingual Text-to-Image Diffusion Model","created":"2023-08-19","cited_by_count":30,"area":"diffusion"},{"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":"2407.17453","title":"VILA$^2$: VILA Augmented VILA","created":"2024-07-24","cited_by_count":25,"area":"mllm"},{"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":"2410.08876","title":"RoRA-VLM: Robust Retrieval-Augmented Vision Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"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":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","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":"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":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"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":"2305.06324","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","created":"2023-05-10","cited_by_count":19,"area":"moe"},{"id":"2401.08053","title":"SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation","created":"2024-01-16","cited_by_count":19,"area":null}],"next_cursor":"100"}