{"list":"other","total":70,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2002.10099","title":"Implicit Geometric Regularization for Learning Shapes","created":"2020-02-24","cited_by_count":710},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365},{"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":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194},{"id":"2010.04595","title":"GRF: Learning a General Radiance Field for 3D Representation and Rendering","created":"2020-10-09","cited_by_count":183},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2303.00905","title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","created":"2023-03-02","cited_by_count":156},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118},{"id":"2303.15951","title":"F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories","created":"2023-03-28","cited_by_count":118},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113},{"id":"2204.02296","title":"iSDF: Real-Time Neural Signed Distance Fields for Robot Perception","created":"2022-04-05","cited_by_count":109},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89},{"id":"2111.09996","title":"LOLNeRF: Learn from One Look","created":"2021-11-19","cited_by_count":84},{"id":"1807.07049","title":"Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias","created":"2018-07-18","cited_by_count":75},{"id":"2303.07798","title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","created":"2023-03-14","cited_by_count":70},{"id":"2112.05251","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","created":"2021-12-09","cited_by_count":59},{"id":"2106.14386","title":"Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems","created":"2021-06-28","cited_by_count":54},{"id":"2108.01176","title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","created":"2021-08-02","cited_by_count":52},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50},{"id":"2303.12786","title":"FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models","created":"2023-03-22","cited_by_count":47},{"id":"2209.02778","title":"Multi-skill Mobile Manipulation for Object Rearrangement","created":"2022-09-06","cited_by_count":46},{"id":"2209.08274","title":"Topological Semantic Graph Memory for Image-Goal Navigation","created":"2022-09-17","cited_by_count":45},{"id":"2304.00410","title":"ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation","created":"2023-04-01","cited_by_count":42},{"id":"2107.13545","title":"Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation","created":"2021-07-28","cited_by_count":35},{"id":"2203.07359","title":"Stubborn: A Strong Baseline for Indoor Object Navigation","created":"2022-03-14","cited_by_count":32},{"id":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","cited_by_count":25},{"id":"2309.15459","title":"GAMMA: Graspability-Aware Mobile MAnipulation Policy Learning based on Online Grasping Pose Fusion","created":"2023-09-27","cited_by_count":22},{"id":"1812.04093","title":"Stable bin packing of non-convex 3D objects with a robot manipulator","created":"2018-12-10","cited_by_count":21},{"id":"2210.05129","title":"Multi-Object Navigation with dynamically learned neural implicit representations","created":"2022-10-11","cited_by_count":21},{"id":"2304.14401","title":"ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs","created":"2023-04-27","cited_by_count":21},{"id":"2112.04063","title":"Semantic OcTree Mapping and Shannon Mutual Information Computation for Robot Exploration","created":"2021-12-08","cited_by_count":16},{"id":"2308.09873","title":"Skill Transformer: A Monolithic Policy for Mobile Manipulation","created":"2023-08-19","cited_by_count":16},{"id":"2106.11857","title":"HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry","created":"2021-06-22","cited_by_count":8},{"id":"2004.00899","title":"Go Fetch: Mobile Manipulation in Unstructured Environments","created":"2020-04-02","cited_by_count":5},{"id":"2309.15164","title":"3D Reconstruction with Generalizable Neural Fields using Scene Priors","created":"2023-09-26","cited_by_count":4},{"id":"2304.11235","title":"Spatial-Language Attention Policies for Efficient Robot Learning","created":"2023-04-21","cited_by_count":3},{"id":"2307.04918","title":"Kinematically-Decoupled Impedance Control for Fast Object Visual Servoing and Grasping on Quadruped Manipulators","created":"2023-07-10","cited_by_count":1}],"next_cursor":null}