{"total":511,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224,"area":"mllm"},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471,"area":"mllm"},{"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":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610,"area":"mllm"},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565,"area":null},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527,"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":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346,"area":"wm"},{"id":"2301.10343","title":"ClimaX: A foundation model for weather and climate","created":"2023-01-24","cited_by_count":337,"area":null},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328,"area":null},{"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":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300,"area":"mllm"},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274,"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":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"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":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187,"area":"diffusion"},{"id":"2502.17422","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","created":"2025-02-24","cited_by_count":176,"area":"mllm"},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174,"area":"mllm"},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172,"area":"mllm"},{"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":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"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":"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":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148,"area":null},{"id":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2306.07831","title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","created":"2023-06-13","cited_by_count":134,"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":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125,"area":"mllm"},{"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":"2212.08320","title":"Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?","created":"2022-12-16","cited_by_count":122,"area":"distill"},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"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":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115,"area":null},{"id":"2210.15257","title":"ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Experts","created":"2022-10-27","cited_by_count":112,"area":"diffusion"},{"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":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2312.12241","title":"GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning","created":"2023-12-19","cited_by_count":108,"area":"lr"},{"id":"2501.18867","title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","created":"2025-01-31","cited_by_count":102,"area":"mllm"},{"id":"2412.18607","title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers","created":"2024-12-24","cited_by_count":96,"area":"wm"},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2304.06798","title":"On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence","created":"2023-04-13","cited_by_count":88,"area":null},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87,"area":null},{"id":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86,"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":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84,"area":null},{"id":"2308.06911","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","created":"2023-08-14","cited_by_count":82,"area":"mllm"},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82,"area":"mllm"},{"id":"2305.01278","title":"VPGTrans: Transfer Visual Prompt Generator across LLMs","created":"2023-05-02","cited_by_count":80,"area":"mllm"},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2302.00673","title":"ADAPT: Action-aware Driving Caption Transformer","created":"2023-02-01","cited_by_count":78,"area":"driving"},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2301.13155","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","created":"2023-01-30","cited_by_count":75,"area":null},{"id":"2410.05273","title":"HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers","created":"2024-09-12","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":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2211.10950","title":"Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models","created":"2022-11-20","cited_by_count":70,"area":"diffusion"},{"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":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69,"area":"mllm"},{"id":"2404.07214","title":"Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions","created":"2024-02-20","cited_by_count":68,"area":"mllm"},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65,"area":null},{"id":"2406.20076","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","created":"2024-06-28","cited_by_count":65,"area":"mllm"},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62,"area":"mllm"},{"id":"2304.05215","title":"A Billion-scale Foundation Model for Remote Sensing Images","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2407.21770","title":"MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts","created":"2024-07-31","cited_by_count":62,"area":"moe"}],"next_cursor":"100"}