{"total":13,"rows":[{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73,"area":null},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2412.01801","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"area":null},{"id":"2504.14151","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","created":"2025-04-19","cited_by_count":23,"area":null},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2412.13897","title":"Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2512.15708","title":"Multi-View Foundation Models","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2605.21258","title":"Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.17564","title":"Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2503.06469","title":"Vector Quantized Feature Fields for Fast 3D Semantic Lifting","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2508.01423","title":"3DRot: Rediscovering the Missing Primitive for RGB-Based 3D Augmentation","created":"2025-08-02","cited_by_count":0,"area":null}],"next_cursor":null}