{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"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":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"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":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"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":"2110.00168","title":"Vision-Only Robot Navigation in a Neural Radiance World","created":"2021-10-01","cited_by_count":155},{"id":"2210.15858","title":"Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation","created":"2022-10-28","cited_by_count":149},{"id":"2110.06558","title":"LENS: Localization enhanced by NeRF synthesis","created":"2021-10-13","cited_by_count":117},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108},{"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":"2303.05657","title":"Tag2Text: Guiding Vision-Language Model via Image Tagging","created":"2023-03-10","cited_by_count":86},{"id":"2311.02873","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","created":"2023-11-06","cited_by_count":81},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67},{"id":"2210.06575","title":"GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF","created":"2022-10-12","cited_by_count":67},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2203.04802","title":"NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation","created":"2022-03-09","cited_by_count":58},{"id":"2303.13483","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","created":"2023-03-23","cited_by_count":57},{"id":"2309.15940","title":"Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs","created":"2023-09-27","cited_by_count":33},{"id":"2310.17109","title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","created":"2023-10-26","cited_by_count":29},{"id":"2110.14573","title":"Autonomous Exploration Development Environment and the Planning Algorithms","created":"2021-10-27","cited_by_count":27},{"id":"1808.00692","title":"Online Temporal Calibration for Monocular Visual-Inertial Systems","created":"2018-08-02","cited_by_count":26},{"id":"1710.01328","title":"Reuleaux: Robot Base Placement by Reachability Analysis","created":"2017-10-03","cited_by_count":11},{"id":"2003.05766","title":"Inertial-Only Optimization for Visual-Inertial Initialization","created":"2020-03-12","cited_by_count":11},{"id":"2009.02869","title":"Frontier Detection and Reachability Analysis for Efficient 2D Graph-SLAM Based Active Exploration","created":"2020-09-07","cited_by_count":3}],"next_cursor":null}