{"list":"other","total":57,"rows":[{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"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":"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2401.15077","title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","created":"2024-01-26","cited_by_count":578},{"id":"2005.04259","title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","created":"2020-05-08","cited_by_count":530},{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490},{"id":"1812.03079","title":"ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst","created":"2018-12-07","cited_by_count":397},{"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":"2008.08294","title":"TNT: Target-driveN Trajectory Prediction","created":"2020-08-19","cited_by_count":347},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"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":"2108.09640","title":"DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets","created":"2021-08-22","cited_by_count":295},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"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":"2101.06679","title":"End-to-end Interpretable Neural Motion Planner","created":"2021-01-17","cited_by_count":242},{"id":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2103.11624","title":"Multimodal Motion Prediction with Stacked Transformers","created":"2021-03-22","cited_by_count":208},{"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":"1911.10868","title":"End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances","created":"2019-11-25","cited_by_count":149},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"2311.01043","title":"LLM4Drive: A Survey of Large Language Models for Autonomous Driving","created":"2023-11-02","cited_by_count":136},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"id":"2309.04379","title":"Language Prompt for Autonomous Driving","created":"2023-09-08","cited_by_count":111},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2003.09405","title":"Explainable Object-induced Action Decision for Autonomous Vehicles","created":"2020-03-20","cited_by_count":88},{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84},{"id":"2210.01917","title":"Differentiable Raycasting for Self-supervised Occupancy Forecasting","created":"2022-10-04","cited_by_count":84},{"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":"2309.06597","title":"Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning","created":"2023-09-12","cited_by_count":63},{"id":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2011.01153","title":"Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving","created":"2020-11-02","cited_by_count":24},{"id":"2309.16397","title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","created":"2023-09-28","cited_by_count":8}],"next_cursor":null}