{"list":"other","total":93,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1812.05784","title":"PointPillars: Fast Encoders for Object Detection from Point Clouds","created":"2018-12-14","cited_by_count":1715},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"2104.10956","title":"FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection","created":"2021-04-22","cited_by_count":447},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"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":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1906.05113","title":"A Survey of Autonomous Driving: Common Practices and Emerging Technologies","created":"2019-06-12","cited_by_count":379},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"id":"2406.15349","title":"NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","created":"2024-06-21","cited_by_count":354},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","cited_by_count":289},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248},{"id":"2206.08920","title":"VectorMapNet: End-to-end Vectorized HD Map Learning","created":"2022-06-17","cited_by_count":245},{"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":"2310.01957","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","created":"2023-10-03","cited_by_count":232},{"id":"2402.11502","title":"GenAD: Generative End-to-End Autonomous Driving","created":"2024-02-18","cited_by_count":225},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"id":"2308.05736","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction","created":"2023-08-10","cited_by_count":193},{"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":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"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":"2308.12570","title":"StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction","created":"2023-08-24","cited_by_count":145},{"id":"2306.17770","title":"MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying","created":"2023-06-30","cited_by_count":140},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114},{"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":"2311.01017","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","created":"2023-11-02","cited_by_count":106},{"id":"1807.03776","title":"CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving","created":"2018-07-10","cited_by_count":97},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92},{"id":"2308.16477","title":"PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction","created":"2023-08-31","cited_by_count":85},{"id":"2306.09700","title":"End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve","created":"2023-06-16","cited_by_count":82},{"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":"2111.08575","title":"GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving","created":"2021-11-16","cited_by_count":60},{"id":"2310.17642","title":"Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models","created":"2023-10-26","cited_by_count":59},{"id":"2303.08815","title":"Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction","created":"2023-03-15","cited_by_count":50},{"id":"2210.09267","title":"CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection","created":"2022-10-17","cited_by_count":30},{"id":"2304.03834","title":"WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting","created":"2023-04-07","cited_by_count":28},{"id":"2206.07705","title":"LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection","created":"2022-06-15","cited_by_count":27},{"id":"2106.05966","title":"Learning by Watching","created":"2021-06-10","cited_by_count":22},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20},{"id":"2312.01990","title":"SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention","created":"2023-12-04","cited_by_count":20},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","cited_by_count":19},{"id":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14},{"id":"2403.05489","title":"JointMotion: Joint Self-Supervision for Joint Motion Prediction","created":"2024-03-08","cited_by_count":7},{"id":"2402.03494","title":"Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks","created":"2024-02-05","cited_by_count":5}],"next_cursor":null}