{"total":383,"rows":[{"id":"2310.01415","title":"GPT-Driver: Learning to Drive with GPT","created":"2023-10-02","cited_by_count":347,"area":null},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","cited_by_count":242,"area":null},{"id":"2401.03890","title":"A Survey on 3D Gaussian Splatting","created":"2024-01-08","cited_by_count":224,"area":null},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209,"area":null},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170,"area":null},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168,"area":null},{"id":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128,"area":null},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106,"area":null},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96,"area":null},{"id":"2506.06659","title":"DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning","created":"2025-06-07","cited_by_count":94,"area":null},{"id":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92,"area":null},{"id":"2306.15670","title":"Symphonize 3D Semantic Scene Completion with Contextual Instance Queries","created":"2023-06-27","cited_by_count":90,"area":null},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83,"area":null},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2311.11722","title":"Sparse4D v3: Advancing End-to-End 3D Detection and Tracking","created":"2023-11-20","cited_by_count":70,"area":null},{"id":"2506.06664","title":"Generalized Trajectory Scoring for End-to-end Multimodal Planning","created":"2025-06-07","cited_by_count":67,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63,"area":null},{"id":"2403.10521","title":"P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors","created":"2024-03-15","cited_by_count":54,"area":null},{"id":"2404.00876","title":"MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction","created":"2024-04-01","cited_by_count":52,"area":null},{"id":"2405.13675","title":"Context and Geometry Aware Voxel Transformer for Semantic Scene Completion","created":"2024-05-22","cited_by_count":50,"area":null},{"id":"2403.08639","title":"HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction","created":"2024-03-13","cited_by_count":48,"area":null},{"id":"2310.06753","title":"TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning","created":"2023-10-10","cited_by_count":41,"area":null},{"id":"2403.19589","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2407.02797","title":"Solving Motion Planning Tasks with a Scalable Generative Model","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2503.15208","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","created":"2025-03-19","cited_by_count":40,"area":null},{"id":"2404.07569","title":"Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?","created":"2024-04-11","cited_by_count":38,"area":null},{"id":"2405.05173","title":"A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective","created":"2024-05-08","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","cited_by_count":36,"area":null},{"id":"2511.23369","title":"SimScale: Learning to Drive via Real-World Simulation at Scale","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2307.06505","title":"WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces","created":"2023-07-13","cited_by_count":35,"area":null},{"id":"2311.15977","title":"Text2Loc: 3D Point Cloud Localization from Natural Language","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2312.01696","title":"BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection","created":"2023-12-04","cited_by_count":35,"area":null},{"id":"2403.07746","title":"Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception","created":"2024-03-12","cited_by_count":35,"area":null},{"id":"2403.11492","title":"SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction","created":"2024-03-18","cited_by_count":34,"area":null},{"id":"2411.11252","title":"DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation","created":"2024-11-18","cited_by_count":34,"area":null},{"id":"2403.16439","title":"Producing and Leveraging Online Map Uncertainty in Trajectory Prediction","created":"2024-03-25","cited_by_count":33,"area":null},{"id":"2405.14014","title":"RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar","created":"2024-05-22","cited_by_count":33,"area":null},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2308.05731","title":"The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2405.14747","title":"TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes","created":"2024-05-23","cited_by_count":29,"area":null},{"id":"2311.07152","title":"Detecting As Labeling: Rethinking LiDAR-camera Fusion in 3D Object Detection","created":"2023-11-13","cited_by_count":28,"area":null},{"id":"2412.04842","title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","created":"2024-12-06","cited_by_count":27,"area":null},{"id":"2405.15677","title":"SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction","created":"2024-05-24","cited_by_count":25,"area":null},{"id":"2308.01804","title":"QUEST: Query Stream for Practical Cooperative Perception","created":"2023-08-03","cited_by_count":23,"area":null},{"id":"2310.11239","title":"LiDAR-based 4D Occupancy Completion and Forecasting","created":"2023-10-17","cited_by_count":23,"area":null},{"id":"2312.00703","title":"PointBeV: A Sparse Approach to BeV Predictions","created":"2023-12-01","cited_by_count":23,"area":null},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2306.09281","title":"Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?","created":"2023-06-15","cited_by_count":22,"area":null},{"id":"2404.00742","title":"Adapting to Length Shift: FlexiLength Network for Trajectory Prediction","created":"2024-03-31","cited_by_count":22,"area":null},{"id":"2405.15688","title":"UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes","created":"2024-05-24","cited_by_count":22,"area":null},{"id":"2406.07661","title":"ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones","created":"2024-06-11","cited_by_count":22,"area":null},{"id":"2408.03624","title":"AgentsCoMerge: Large Language Model Empowered Collaborative Decision Making for Ramp Merging","created":"2024-08-07","cited_by_count":22,"area":null},{"id":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"area":null},{"id":"2403.10052","title":"T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory","created":"2024-03-15","cited_by_count":20,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2506.10977","title":"QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction","created":"2025-06-12","cited_by_count":20,"area":null},{"id":"2306.15700","title":"Imitation with Spatial-Temporal Heatmap: 2nd Place Solution for NuPlan Challenge","created":"2023-06-26","cited_by_count":19,"area":null},{"id":"2503.12552","title":"MTGS: Multi-Traversal Gaussian Splatting","created":"2025-03-16","cited_by_count":19,"area":null},{"id":"2512.19021","title":"VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation","created":"2025-12-22","cited_by_count":19,"area":null},{"id":"2403.06122","title":"Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2404.05094","title":"Active Test-Time Adaptation: Theoretical Analyses and An Algorithm","created":"2024-04-07","cited_by_count":18,"area":null},{"id":"2406.09383","title":"Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset","created":"2024-06-13","cited_by_count":18,"area":null},{"id":"2304.08600","title":"RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding","created":"2023-04-17","cited_by_count":17,"area":null},{"id":"2311.13250","title":"FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning","created":"2023-11-22","cited_by_count":17,"area":null},{"id":"2407.15349","title":"RoadPainter: Points Are Ideal Navigators for Topology transformER","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2404.02517","title":"HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras","created":"2024-04-03","cited_by_count":16,"area":null},{"id":"2502.11534","title":"SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking","created":"2025-02-17","cited_by_count":16,"area":null},{"id":"2305.18829","title":"UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving","created":"2023-05-30","cited_by_count":15,"area":null},{"id":"2306.06849","title":"Mitigating Transformer Overconfidence via Lipschitz Regularization","created":"2023-06-12","cited_by_count":15,"area":null},{"id":"2309.14655","title":"Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2406.04426","title":"DeTra: A Unified Model for Object Detection and Trajectory Forecasting","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2408.02061","title":"ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning","created":"2024-08-04","cited_by_count":15,"area":null},{"id":"2410.05111","title":"LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2411.14716","title":"VisionPAD: A Vision-Centric Pre-training Paradigm for Autonomous Driving","created":"2024-11-22","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2401.12422","title":"InverseMatrixVT3D: An Efficient Projection Matrix-Based Approach for 3D Occupancy Prediction","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2403.08919","title":"CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow","created":"2024-03-13","cited_by_count":14,"area":null},{"id":"2502.16589","title":"Co-MTP: A Cooperative Trajectory Prediction Framework with Multi-Temporal Fusion for Autonomous Driving","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2505.10685","title":"GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention","created":"2025-05-15","cited_by_count":14,"area":null},{"id":"2310.15670","title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","created":"2023-10-24","cited_by_count":13,"area":null},{"id":"2403.11127","title":"GRA: Detecting Oriented Objects through Group-wise Rotating and Attention","created":"2024-03-17","cited_by_count":13,"area":null},{"id":"2409.10063","title":"GlobalMapNet: An Online Framework for Vectorized Global HD Map Construction","created":"2024-09-16","cited_by_count":13,"area":null},{"id":"2502.14503","title":"LXLv2: Enhanced LiDAR Excluded Lean 3D Object Detection with Fusion of 4D Radar and Camera","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2406.10722","title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","created":"2024-06-15","cited_by_count":12,"area":null},{"id":"2411.11002","title":"Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2503.14945","title":"Generating Multimodal Driving Scenes via Next-Scene Prediction","created":"2025-03-19","cited_by_count":12,"area":null},{"id":"2503.22231","title":"CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2504.10485","title":"Decoupled Diffusion Sparks Adaptive Scene Generation","created":"2025-04-14","cited_by_count":12,"area":null},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2403.06828","title":"NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2407.11700","title":"Rate-Distortion-Cognition Controllable Versatile Neural Image Compression","created":"2024-07-16","cited_by_count":11,"area":null}],"next_cursor":"100"}