{"list":"other","total":70,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2406.15349","title":"NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","created":"2024-06-21","cited_by_count":354},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2411.15139","title":"DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving","created":"2024-11-22","cited_by_count":334},{"id":"1603.02199","title":"Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection","created":"2016-03-07","cited_by_count":316},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2410.06158","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","created":"2024-10-08","cited_by_count":296},{"id":"2406.03877","title":"Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving","created":"2024-06-06","cited_by_count":252},{"id":"2406.06978","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","created":"2024-06-11","cited_by_count":249},{"id":"2306.07962","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning","created":"2023-06-13","cited_by_count":242},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2203.06026","title":"The Role of ImageNet Classes in Fr\\'echet Inception Distance","created":"2022-03-11","cited_by_count":213},{"id":"1509.06825","title":"Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours","created":"2015-09-23","cited_by_count":209},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185},{"id":"2503.23463","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","created":"2025-03-30","cited_by_count":176},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"2506.04218","title":"Pseudo-Simulation for Autonomous Driving","created":"2025-06-04","cited_by_count":150},{"id":"2501.15564","title":"Diffusion-Based Planning for Autonomous Driving with Flexible Guidance","created":"2025-01-26","cited_by_count":141},{"id":"2308.10832","title":"EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition","created":"2023-08-21","cited_by_count":111},{"id":"2404.14327","title":"PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving","created":"2024-04-22","cited_by_count":84},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68},{"id":"2510.26125","title":"WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios","created":"2025-10-30","cited_by_count":62},{"id":"2502.17237","title":"MegaLoc: One Retrieval to Place Them All","created":"2025-02-24","cited_by_count":60},{"id":"2406.11819","title":"MegaScenes: Scene-Level View Synthesis at Scale","created":"2024-06-17","cited_by_count":58},{"id":"2407.02598","title":"AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction","created":"2024-07-02","cited_by_count":52},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44},{"id":"1911.04074","title":"SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic","created":"2019-11-11","cited_by_count":40},{"id":"2504.13157","title":"AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis","created":"2025-04-17","cited_by_count":39},{"id":"2404.07569","title":"Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?","created":"2024-04-11","cited_by_count":38},{"id":"2403.17933","title":"SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic","created":"2024-03-26","cited_by_count":27},{"id":"2504.20040","title":"MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion","created":"2025-04-28","cited_by_count":26},{"id":"2309.10443","title":"Rethinking Imitation-based Planner for Autonomous Driving","created":"2023-09-19","cited_by_count":25},{"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},{"id":"1710.08247","title":"Generic 3D Representation via Pose Estimation and Matching","created":"2017-10-23","cited_by_count":17},{"id":"2604.08535","title":"Fail2Drive: Benchmarking Closed-Loop Driving Generalization","created":"2026-04-09","cited_by_count":17},{"id":"2007.13078","title":"SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction","created":"2020-07-26","cited_by_count":15},{"id":"2509.26639","title":"Benchmarking Egocentric Visual-Inertial SLAM at City Scale","created":"2025-09-30","cited_by_count":14},{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14},{"id":"2510.26795","title":"Scaling Image Geo-Localization to Continent Level","created":"2025-10-30","cited_by_count":10},{"id":"2605.26103","title":"Global Structure-from-Motion Meets Feedforward Reconstruction","created":"2026-05-25","cited_by_count":8},{"id":"2311.04243","title":"Toward Planet-Wide Traffic Camera Calibration","created":"2023-11-06","cited_by_count":7},{"id":"2510.14677","title":"When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks","created":"2025-10-16","cited_by_count":7},{"id":"2003.11766","title":"DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems","created":"2020-03-26","cited_by_count":6},{"id":"2506.12563","title":"Benchmarking Image Similarity Metrics for Novel View Synthesis Applications","created":"2025-06-14","cited_by_count":5},{"id":"2506.20553","title":"Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation","created":"2025-06-25","cited_by_count":5},{"id":"2603.23607","title":"Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset","created":"2026-03-24","cited_by_count":4},{"id":"2603.28522","title":"RAD-LAD: Rule and Language Grounded Autonomous Driving in Real-Time","created":"2026-03-30","cited_by_count":3},{"id":"2605.22809","title":"Sensor2Sensor: Cross-Embodiment Sensor Conversion for Autonomous Driving","created":"2026-05-21","cited_by_count":3}],"next_cursor":null}