{"total":19,"rows":[{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"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":"2503.21770","title":"Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting","created":"2025-03-27","cited_by_count":11,"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":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2511.11470","title":"Sat2RealCity: Geometry-Aware and Appearance-Controllable 3D Urban Generation from Satellite Imagery","created":"2025-11-14","cited_by_count":7,"area":null},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2411.16668","title":"Diffusion Features for Zero-Shot 6DoF Object Pose Estimation","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2511.12675","title":"Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis","created":"2025-11-16","cited_by_count":4,"area":null},{"id":"2609.04200","title":"Principia: Relational Physics Tests for Video Models","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2404.11554","title":"Predicting Long-horizon Futures by Conditioning on Geometry and Time","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2509.05285","title":"Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2606.03986","title":"NewtPhys: Do Foundation Models Understand Newtonian Physics?","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.05393","title":"Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.01495","title":"Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.10131","title":"P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing","created":"2026-08-10","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}],"next_cursor":null}