{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2112.11790","title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","created":"2021-12-22","cited_by_count":713},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2205.15997","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","created":"2022-05-31","cited_by_count":485},{"id":"2310.01412","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","created":"2023-10-02","cited_by_count":461},{"id":"1910.05449","title":"MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction","created":"2019-10-12","cited_by_count":420},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"2104.09224","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","created":"2021-04-19","cited_by_count":377},{"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":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"2208.14437","title":"MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction","created":"2022-08-30","cited_by_count":314},{"id":"2402.13243","title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","created":"2024-02-20","cited_by_count":289},{"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":"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":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2312.09245","title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","created":"2023-12-14","cited_by_count":233},{"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":"1807.11546","title":"Textual Explanations for Self-Driving Vehicles","created":"2018-07-30","cited_by_count":226},{"id":"2402.11502","title":"GenAD: Generative End-to-End Autonomous Driving","created":"2024-02-18","cited_by_count":225},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194},{"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":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"1906.03560","title":"Cross-view Semantic Segmentation for Sensing Surroundings","created":"2019-06-09","cited_by_count":174},{"id":"2410.22313","title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","created":"2024-10-29","cited_by_count":156},{"id":"2008.05930","title":"Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations","created":"2020-08-13","cited_by_count":153},{"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":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2403.16387","title":"Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion","created":"2024-03-25","cited_by_count":84},{"id":"2204.00102","title":"Dynamic Multimodal Fusion","created":"2022-03-31","cited_by_count":55},{"id":"1910.04586","title":"Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles","created":"2019-10-10","cited_by_count":51},{"id":"2003.06409","title":"Probabilistic Future Prediction for Video Scene Understanding","created":"2020-03-13","cited_by_count":45},{"id":"2006.11436","title":"BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud","created":"2020-06-19","cited_by_count":38},{"id":"2212.02181","title":"Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction","created":"2022-12-05","cited_by_count":28},{"id":"1808.00327","title":"Generative Adversarial Frontal View to Bird View Synthesis","created":"2018-08-01","cited_by_count":25},{"id":"2104.12861","title":"Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation","created":"2021-04-18","cited_by_count":25},{"id":"2008.04047","title":"Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning","created":"2020-08-10","cited_by_count":24},{"id":"2407.12345","title":"VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions","created":"2024-07-17","cited_by_count":19},{"id":"2501.08168","title":"LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking","created":"2025-01-14","cited_by_count":13},{"id":"2412.06324","title":"World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving","created":"2024-12-09","cited_by_count":9},{"id":"2312.14446","title":"Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset","created":"2023-12-22","cited_by_count":8}],"next_cursor":null}