{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"2403.11703","title":"LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images","created":"2024-03-18","cited_by_count":195},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2408.15542","title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input","created":"2024-08-28","cited_by_count":134},{"id":"2402.11530","title":"Efficient Multimodal Learning from Data-centric Perspective","created":"2024-02-18","cited_by_count":122},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"id":"2408.14023","title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos","created":"2024-08-26","cited_by_count":98},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73},{"id":"2403.12966","title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","created":"2024-03-19","cited_by_count":66},{"id":"2403.18361","title":"ViTAR: Vision Transformer with Any Resolution","created":"2024-03-27","cited_by_count":25},{"id":"2407.18121","title":"Efficient Inference of Vision Instruction-Following Models with Elastic Cache","created":"2024-07-25","cited_by_count":24}],"next_cursor":null}