{"total":24,"rows":[{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2502.19128","title":"SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2510.10287","title":"Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking","created":"2025-10-11","cited_by_count":9,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","cited_by_count":7,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.06719","title":"Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding","created":"2025-04-09","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":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2603.12579","title":"DINOLight: Robust Ambient Light Normalization with Self-supervised Visual Prior Integration","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2606.04010","title":"The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.14228","title":"SeeSE3: Emergence of 3D Space in Vision Features","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2601.18929","title":"On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.22529","title":"SHED Light on Segmentation for Dense Prediction","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2607.16274","title":"The JEPA Predictor: A Transferable Operator for Occluded Feature Completion","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.27226","title":"DINOcular: Self-Supervised Visuospatial Representations","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.20323","title":"NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.02974","title":"From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12926","title":"What Egocentric Video Embeddings Encode and How to Combine Them with Inertial Sensors for Human Activity Recognition","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}