{"list":"other","total":55,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"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":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"2310.01415","title":"GPT-Driver: Learning to Drive with GPT","created":"2023-10-02","cited_by_count":347},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"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},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2312.03031","title":"Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?","created":"2023-12-05","cited_by_count":242},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2305.10430","title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","created":"2023-05-17","cited_by_count":191},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"2302.12766","title":"Language-Driven Representation Learning for Robotics","created":"2023-02-24","cited_by_count":165},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126},{"id":"2401.05577","title":"VLP: Vision Language Planning for Autonomous Driving","created":"2024-01-10","cited_by_count":126},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114},{"id":"2203.07724","title":"CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving","created":"2022-03-15","cited_by_count":100},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83},{"id":"1911.06978","title":"Grounding Human-to-Vehicle Advice for Self-driving Vehicles","created":"2019-11-16","cited_by_count":71},{"id":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63},{"id":"2306.04811","title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","created":"2023-06-07","cited_by_count":47},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43},{"id":"2406.14556","title":"Asynchronous Large Language Model Enhanced Planner for Autonomous Driving","created":"2024-06-20","cited_by_count":38},{"id":"1609.04741","title":"Joint Attention in Autonomous Driving (JAAD)","created":"2016-09-15","cited_by_count":36},{"id":"2404.08561","title":"IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic","created":"2024-04-12","cited_by_count":13}],"next_cursor":null}