{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2310.07896","title":"NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration","created":"2023-10-11","cited_by_count":248},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104},{"id":"2410.07408","title":"Automated Creation of Digital Cousins for Robust Policy Learning","created":"2024-10-09","cited_by_count":91},{"id":"2303.03480","title":"Can an Embodied Agent Find Your \"Cat-shaped Mug\"? LLM-Guided Exploration for Zero-Shot Object Navigation","created":"2023-03-06","cited_by_count":74},{"id":"2306.12241","title":"ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling","created":"2023-06-21","cited_by_count":60},{"id":"2503.24361","title":"Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation","created":"2025-03-31","cited_by_count":46},{"id":"2411.17820","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","created":"2024-11-26","cited_by_count":41},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30},{"id":"1712.01397","title":"Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Cars","created":"2017-12-04","cited_by_count":26},{"id":"2212.04819","title":"Phone2Proc: Bringing Robust Robots Into Our Chaotic World","created":"2022-12-08","cited_by_count":26},{"id":"2111.06889","title":"DriverGym: Democratising Reinforcement Learning for Autonomous Driving","created":"2021-11-12","cited_by_count":23},{"id":"2407.08725","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","created":"2024-07-11","cited_by_count":21},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21},{"id":"2504.07334","title":"Objaverse++: Curated 3D Object Dataset with Quality Annotations","created":"2025-04-09","cited_by_count":20},{"id":"2505.00690","title":"Towards Autonomous Micromobility through Scalable Urban Simulation","created":"2025-05-01","cited_by_count":16},{"id":"2505.05592","title":"Learning to Drive Anywhere with Model-Based Reannotation","created":"2025-05-08","cited_by_count":13},{"id":"2403.20318","title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","created":"2024-03-29","cited_by_count":12},{"id":"2507.22028","title":"From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning","created":"2025-07-29","cited_by_count":12},{"id":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7}],"next_cursor":null}