{"list":"other","total":74,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"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":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233},{"id":"2402.14289","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","created":"2024-02-22","cited_by_count":164},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97},{"id":"2310.10076","title":"Verbosity Bias in Preference Labeling by Large Language Models","created":"2023-10-16","cited_by_count":91},{"id":"2011.03807","title":"Sim-to-Real Transfer for Vision-and-Language Navigation","created":"2020-11-07","cited_by_count":89},{"id":"2402.04833","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","created":"2024-02-07","cited_by_count":85},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79},{"id":"2007.14626","title":"Object-and-Action Aware Model for Visual Language Navigation","created":"2020-07-29","cited_by_count":77},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69},{"id":"2004.02707","title":"Sub-Instruction Aware Vision-and-Language Navigation","created":"2020-04-06","cited_by_count":66},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64},{"id":"2111.12872","title":"Less is More: Generating Grounded Navigation Instructions from Landmarks","created":"2021-11-25","cited_by_count":64},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64},{"id":"2110.14143","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","created":"2021-10-27","cited_by_count":53},{"id":"2101.10504","title":"On the Evaluation of Vision-and-Language Navigation Instructions","created":"2021-01-26","cited_by_count":45},{"id":"1807.03367","title":"Talk the Walk: Navigating New York City through Grounded Dialogue","created":"2018-07-09","cited_by_count":44},{"id":"2303.08409","title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","created":"2023-03-15","cited_by_count":40},{"id":"2105.08612","title":"SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data","created":"2021-05-18","cited_by_count":38},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34},{"id":"2405.03690","title":"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs","created":"2024-05-06","cited_by_count":30},{"id":"2408.06627","title":"WorldScribe: Towards Context-Aware Live Visual Descriptions","created":"2024-08-13","cited_by_count":27},{"id":"2404.02508","title":"VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments","created":"2024-04-03","cited_by_count":25},{"id":"2011.08277","title":"Where Are You? Localization from Embodied Dialog","created":"2020-11-16","cited_by_count":24},{"id":"2407.07433","title":"Controllable Navigation Instruction Generation with Chain of Thought Prompting","created":"2024-07-10","cited_by_count":21},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21},{"id":"2408.11051","title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","created":"2024-08-20","cited_by_count":19},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18},{"id":"2403.12415","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","created":"2024-03-19","cited_by_count":14},{"id":"1804.04118","title":"Personalized Dynamics Models for Adaptive Assistive Navigation Systems","created":"2018-04-11","cited_by_count":13},{"id":"2410.04005","title":"Enhancing the Travel Experience for People with Visual Impairments through Multimodal Interaction: NaviGPT, A Real-Time AI-Driven Mobile Navigation System","created":"2024-10-05","cited_by_count":13},{"id":"1610.03164","title":"Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation","created":"2016-10-11","cited_by_count":12},{"id":"2307.13368","title":"Kefa: A Knowledge Enhanced and Fine-grained Aligned Speaker for Navigation Instruction Generation","created":"2023-07-25","cited_by_count":12},{"id":"2207.11810","title":"VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments","created":"2022-07-24","cited_by_count":11},{"id":"2410.20666","title":"Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairments","created":"2024-10-28","cited_by_count":10},{"id":"2309.04370","title":"Seeing-Eye Quadruped Navigation with Force Responsive Locomotion Control","created":"2023-09-08","cited_by_count":3},{"id":"2412.05277","title":"Text to Blind Motion","created":"2024-12-06","cited_by_count":3},{"id":"2409.11403","title":"UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning","created":"2024-09-17","cited_by_count":2}],"next_cursor":null}