{"total":22,"rows":[{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2212.04385","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","created":"2022-12-08","cited_by_count":122,"area":null},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77,"area":null},{"id":"2303.13450","title":"Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes","created":"2023-03-23","cited_by_count":75,"area":null},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43,"area":null},{"id":"2407.05388","title":"Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2209.07105","title":"Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2503.09938","title":"PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2506.08566","title":"Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2210.04522","title":"HORIZON: High-Resolution Semantically Controlled Panorama Synthesis","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2403.13947","title":"BlendScape: Enabling End-User Customization of Video-Conferencing Environments through Generative AI","created":"2024-03-20","cited_by_count":3,"area":null},{"id":"2505.15765","title":"Constructing a 3D Scene from a Single Image","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2412.06413","title":"World-Consistent Data Generation for Vision-and-Language Navigation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2406.19967","title":"Into the Unknown: Generating Geospatial Descriptions for New Environments","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2607.05765","title":"Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2310.07021","title":"Pre-Trained Masked Image Model for Mobile Robot Navigation","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2412.14005","title":"Real-Time Position-Aware View Synthesis from Single-View Input","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2503.20289","title":"HierRelTriple: Guiding Indoor Layout Generation with Hierarchical Relationship Triplet Losses","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2606.19948","title":"Advancing DialNav through Automatic Embodied Dialog Augmentation","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}