{"list":"other","total":83,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"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":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"2507.05240","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","created":"2025-07-07","cited_by_count":118},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117},{"id":"2405.17958","title":"FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes","created":"2024-05-28","cited_by_count":89},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2509.12129","title":"Embodied Navigation Foundation Model","created":"2025-09-15","cited_by_count":72},{"id":"2003.00368","title":"The Marathon 2: A Navigation System","created":"2020-03-01","cited_by_count":70},{"id":"2512.08186","title":"Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation","created":"2025-12-09","cited_by_count":62},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60},{"id":"2601.22158","title":"One-step Latent-free Image Generation with Pixel Mean Flows","created":"2026-01-29","cited_by_count":53},{"id":"2208.11781","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","created":"2022-08-24","cited_by_count":50},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48},{"id":"2511.07321","title":"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting","created":"2025-11-10","cited_by_count":37},{"id":"2204.02960","title":"Simple and Effective Synthesis of Indoor 3D Scenes","created":"2022-04-06","cited_by_count":33},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30},{"id":"2507.13019","title":"Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities","created":"2025-07-17","cited_by_count":25},{"id":"2412.06250","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","created":"2024-12-09","cited_by_count":24},{"id":"2510.11712","title":"DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training","created":"2025-10-13","cited_by_count":24},{"id":"2505.11383","title":"Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation","created":"2025-05-16","cited_by_count":23},{"id":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20},{"id":"2502.11142","title":"NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM","created":"2025-02-16","cited_by_count":19},{"id":"2512.19021","title":"VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation","created":"2025-12-22","cited_by_count":19},{"id":"2510.21307","title":"Towards Physically Executable 3D Gaussian for Embodied Navigation","created":"2025-10-24","cited_by_count":17},{"id":"2602.11337","title":"MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation","created":"2026-02-11","cited_by_count":14},{"id":"2509.17430","title":"EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device","created":"2025-09-22","cited_by_count":12},{"id":"2511.17097","title":"Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation","created":"2025-11-21","cited_by_count":12},{"id":"2307.15236","title":"From the Desks of ROS Maintainers: A Survey of Modern & Capable Mobile Robotics Algorithms in the Robot Operating System 2","created":"2023-07-28","cited_by_count":11},{"id":"2412.16604","title":"OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities","created":"2024-12-21","cited_by_count":10},{"id":"2305.20026","title":"Regulated Pure Pursuit for Robot Path Tracking","created":"2023-05-31","cited_by_count":8},{"id":"2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","created":"2025-12-14","cited_by_count":5},{"id":"2602.11575","title":"ReaDy-Go: Real-to-Sim Dynamic 3D Gaussian Splatting Simulation for Environment-Specific Visual Navigation with Moving Obstacles","created":"2026-02-12","cited_by_count":5},{"id":"2603.13833","title":"ImagiNav: Scalable Embodied Navigation via Generative Visual Prediction and Inverse Dynamics","created":"2026-03-14","cited_by_count":5},{"id":"2512.10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","created":"2025-12-11","cited_by_count":4},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3},{"id":"2603.15186","title":"NavGSim: High-Fidelity Gaussian Splatting Simulator for Large-Scale Navigation","created":"2026-03-16","cited_by_count":2}],"next_cursor":null}