{"list":"other","total":51,"rows":[{"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":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2303.07418","title":"FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization","created":"2023-03-13","cited_by_count":311},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222},{"id":"2502.09560","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","created":"2025-02-13","cited_by_count":221},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"2410.07166","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","created":"2024-10-09","cited_by_count":144},{"id":"2403.15704","title":"Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections","created":"2024-03-23","cited_by_count":117},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"2005.08135","title":"VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change","created":"2020-05-17","cited_by_count":101},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56},{"id":"2406.14240","title":"CityNav: A Large-Scale Dataset for Real-World Aerial Navigation","created":"2024-06-20","cited_by_count":42},{"id":"2410.09604","title":"EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment","created":"2024-10-12","cited_by_count":42},{"id":"2411.17820","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos","created":"2024-11-26","cited_by_count":41},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30},{"id":"2503.14607","title":"Can Large Vision Language Models Read Maps Like a Human?","created":"2025-03-18","cited_by_count":30},{"id":"2506.01952","title":"WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks","created":"2025-06-02","cited_by_count":30},{"id":"2406.13945","title":"CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks","created":"2024-06-20","cited_by_count":27},{"id":"2012.15329","title":"Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem","created":"2020-12-30","cited_by_count":22},{"id":"2407.08725","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","created":"2024-07-11","cited_by_count":21},{"id":"2506.15677","title":"Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence","created":"2025-06-18","cited_by_count":15},{"id":"2402.03561","title":"VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation","created":"2024-02-05","cited_by_count":14},{"id":"2409.15451","title":"Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models","created":"2024-09-23","cited_by_count":12},{"id":"1909.08970","title":"RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation","created":"2019-09-19","cited_by_count":11},{"id":"2512.16755","title":"CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?","created":"2025-12-18","cited_by_count":8},{"id":"2410.17839","title":"Few-shot NeRF by Adaptive Rendering Loss Regularization","created":"2024-10-23","cited_by_count":6},{"id":"1701.09135","title":"DeepNav: Learning to Navigate Large Cities","created":"2017-01-31","cited_by_count":4},{"id":"2011.08525","title":"Building Movie Map -- A Tool for Exploring Areas in a City -- and its Evaluation","created":"2020-11-17","cited_by_count":4},{"id":"2410.04419","title":"LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation","created":"2024-10-06","cited_by_count":4},{"id":"2606.16953","title":"SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks","created":"2026-06-15","cited_by_count":2},{"id":"2510.11447","title":"Building and Evaluating a Realistic Virtual World for Large Scale Urban Exploration from 360{\\deg} Videos","created":"2025-10-13","cited_by_count":1}],"next_cursor":null}