{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"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":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"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":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2305.18292","title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","created":"2023-05-29","cited_by_count":261},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2311.13600","title":"ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs","created":"2023-11-22","cited_by_count":194},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"2409.02889","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture","created":"2024-09-04","cited_by_count":102},{"id":"2402.16843","title":"Multi-LoRA Composition for Image Generation","created":"2024-02-26","cited_by_count":80},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53},{"id":"1907.01166","title":"Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems","created":"2019-07-02","cited_by_count":52},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29},{"id":"2312.11897","title":"Text-Conditioned Resampler For Long Form Video Understanding","created":"2023-12-19","cited_by_count":24},{"id":"2405.15279","title":"Towards Global Optimal Visual In-Context Learning Prompt Selection","created":"2024-05-24","cited_by_count":15},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11},{"id":"2407.14872","title":"Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts","created":"2024-07-20","cited_by_count":10},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8}],"next_cursor":null}