{"total":20,"rows":[{"id":"2510.26796","title":"See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting","created":"2025-10-30","cited_by_count":12,"area":null},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2510.10660","title":"Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping","created":"2025-10-12","cited_by_count":7,"area":null},{"id":"2511.20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2603.08403","title":"SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents","created":"2026-03-09","cited_by_count":5,"area":null},{"id":"2512.24385","title":"Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2605.08712","title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2603.25494","title":"AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2606.02510","title":"Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.29020","title":"Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2510.07871","title":"Learning to Navigate Socially Through Proactive Risk Perception","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.19488","title":"Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2604.01081","title":"ProOOD: Prototype-Guided Out-of-Distribution 3D Occupancy Prediction","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.07923","title":"Stitch4D: Sparse Multi-Location 4D Urban Reconstruction via Spatio-Temporal Interpolation","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2610.11376","title":"CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}