{"total":327,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869,"area":null},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708,"area":null},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"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":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197,"area":null},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"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":"2403.11207","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","created":"2024-03-17","cited_by_count":109,"area":null},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"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":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"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":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","cited_by_count":71,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64,"area":null},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61,"area":null},{"id":"2211.09808","title":"Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2307.12914","title":"Towards a Visual-Language Foundation Model for Computational Pathology","created":"2023-07-24","cited_by_count":52,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"area":null},{"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":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"area":null},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2306.00864","title":"A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics","created":"2023-06-01","cited_by_count":43,"area":null},{"id":"2303.12060","title":"VideoXum: Cross-modal Visual and Textural Summarization of Videos","created":"2023-03-21","cited_by_count":41,"area":null},{"id":"2309.13952","title":"VidChapters-7M: Video Chapters at Scale","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2310.08541","title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2404.12630","title":"MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction","created":"2024-04-19","cited_by_count":32,"area":null},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31,"area":null},{"id":"2312.00869","title":"Segment and Caption Anything","created":"2023-12-01","cited_by_count":30,"area":null},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2311.17944","title":"PALM: Predicting Actions through Language Models","created":"2023-11-29","cited_by_count":29,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2407.14563","title":"Learning Visual Grounding from Generative Vision and Language Model","created":"2024-07-18","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":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24,"area":null},{"id":"2304.02173","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","created":"2023-04-05","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":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23,"area":null},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2306.11593","title":"Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2310.18049","title":"Text Augmented Spatial-aware Zero-shot Referring Image Segmentation","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2312.07814","title":"A Foundational Multimodal Vision Language AI Assistant for Human Pathology","created":"2023-12-13","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":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"area":null},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19,"area":null},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","cited_by_count":19,"area":null},{"id":"2507.11336","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","created":"2025-07-15","cited_by_count":19,"area":null},{"id":"2208.06551","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","created":"2022-08-13","cited_by_count":18,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2310.13257","title":"Visual Grounding Helps Learn Word Meanings in Low-Data Regimes","created":"2023-10-20","cited_by_count":17,"area":null},{"id":"2311.02538","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","created":"2023-11-05","cited_by_count":17,"area":null},{"id":"2406.02547","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","created":"2024-06-04","cited_by_count":17,"area":null},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","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":"2509.22485","title":"Group Critical-token Policy Optimization for Autoregressive Image Generation","created":"2025-09-26","cited_by_count":17,"area":null},{"id":"2505.06934","title":"Whitened CLIP as a Likelihood Surrogate of Images and Captions","created":"2025-05-11","cited_by_count":16,"area":null}],"next_cursor":"100"}