{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2308.01557","title":"Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models","created":"2023-08-03","cited_by_count":161},{"id":"2406.01733","title":"Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching","created":"2024-06-03","cited_by_count":142},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"2306.11719","title":"Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision","created":"2023-06-20","cited_by_count":112},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106},{"id":"1604.03670","title":"Interactive Perception: Leveraging Action in Perception and Perception in Action","created":"2016-04-13","cited_by_count":78},{"id":"2207.00254","title":"A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers","created":"2022-07-01","cited_by_count":66},{"id":"2107.07599","title":"Partially Observable Markov Decision Processes (POMDPs) and Robotics","created":"2021-07-15","cited_by_count":49},{"id":"2109.10892","title":"The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environments","created":"2021-09-22","cited_by_count":40},{"id":"2306.13196","title":"DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability","created":"2023-06-22","cited_by_count":22},{"id":"2006.10807","title":"Semantic Linking Maps for Active Visual Object Search","created":"2020-06-18","cited_by_count":18},{"id":"2309.14545","title":"Motions in Microseconds via Vectorized Sampling-Based Planning","created":"2023-09-25","cited_by_count":17},{"id":"1705.10907","title":"Provably Safe Robot Navigation with Obstacle Uncertainty","created":"2017-05-31","cited_by_count":12},{"id":"2403.11985","title":"SceneSense: Diffusion Models for 3D Occupancy Synthesis from Partial Observation","created":"2024-03-18","cited_by_count":8},{"id":"2503.07504","title":"PIPE Planner: Pathwise Information Gain with Map Predictions for Indoor Robot Exploration","created":"2025-03-10","cited_by_count":5},{"id":"2410.05869","title":"Believing is Seeing: Unobserved Object Detection using Generative Models","created":"2024-10-08","cited_by_count":4},{"id":"2509.19851","title":"Where Did I Leave My Glasses? Open-Vocabulary Semantic Exploration in Real-World Semi-Static Environments","created":"2025-09-24","cited_by_count":3}],"next_cursor":null}