{"total":79,"rows":[{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566,"area":null},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170,"area":"wm"},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95,"area":"diffusion"},{"id":"2407.04699","title":"LaRa: Efficient Large-Baseline Radiance Fields","created":"2024-07-05","cited_by_count":55,"area":null},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50,"area":null},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"area":null},{"id":"2312.06583","title":"3D Hand Pose Estimation in Everyday Egocentric Images","created":"2023-12-11","cited_by_count":34,"area":null},{"id":"2512.03422","title":"What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models","created":"2025-12-03","cited_by_count":29,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2603.25716","title":"Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models","created":"2026-03-26","cited_by_count":26,"area":"wm"},{"id":"2410.18979","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","created":"2024-10-24","cited_by_count":19,"area":null},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2505.15185","title":"MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models","created":"2025-05-21","cited_by_count":16,"area":null},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2602.07854","title":"Geometry-Aware Rotary Position Embedding for Consistent Video World Model","created":"2026-02-08","cited_by_count":12,"area":"wm"},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2606.09507","title":"Prisma-World: Camera-Controllable Multi-Agent Video World Model","created":"2026-06-08","cited_by_count":11,"area":"wm"},{"id":"2406.20077","title":"HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model","created":"2024-06-28","cited_by_count":9,"area":"diffusion"},{"id":"2602.21341","title":"Scaling View Synthesis Transformers","created":"2026-02-24","cited_by_count":9,"area":null},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2604.18215","title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","created":"2026-04-20","cited_by_count":7,"area":null},{"id":"2411.14762","title":"Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction","created":"2024-11-22","cited_by_count":6,"area":null},{"id":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2604.18747","title":"URoPE: Universal Relative Position Embedding across Geometric Spaces","created":"2026-04-20","cited_by_count":6,"area":null},{"id":"2606.10135","title":"BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression","created":"2026-06-08","cited_by_count":6,"area":"wm"},{"id":"2509.14630","title":"Toward Embodiment Equivariant Vision-Language-Action Policy","created":"2025-09-18","cited_by_count":5,"area":"vla"},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2608.13391","title":"Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation","created":"2026-08-13","cited_by_count":5,"area":"distill"},{"id":"2608.13489","title":"DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation","created":"2026-08-13","cited_by_count":5,"area":"wm"},{"id":"2312.06594","title":"Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2511.22264","title":"DriveVGGT: Calibration-Constrained Visual Geometry Transformers for Multi-Camera Autonomous Driving","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2605.12938","title":"CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation","created":"2026-05-13","cited_by_count":4,"area":"wm"},{"id":"2603.17375","title":"Stereo World Model: Camera-Guided Stereo Video Generation","created":"2026-03-18","cited_by_count":3,"area":"wm"},{"id":"2604.07904","title":"Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2505.01212","title":"High Dynamic Range Novel View Synthesis with Single Exposure","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2506.03753","title":"HUMOF: Human Motion Forecasting in Interactive Social Scenes","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2512.10959","title":"StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.02548","title":"SemGS: Feed-Forward Semantic 3D Gaussian Splatting from Sparse Views for Generalizable Scene Understanding","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2603.14498","title":"R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.21064","title":"2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting","created":"2026-03-22","cited_by_count":2,"area":null},{"id":"2604.01577","title":"Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.31336","title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","created":"2026-05-29","cited_by_count":2,"area":"wm"},{"id":"2606.11275","title":"RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2503.09911","title":"Inter-environmental world modeling for continuous and compositional dynamics","created":"2025-03-13","cited_by_count":1,"area":"wm"},{"id":"2604.13521","title":"C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.25220","title":"Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.31585","title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.24591","title":"CameraAnything: Refilming Videos with Arbitrary Camera Control","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.24136","title":"Steering Recurrent Reasoners at Inference Time with Readout Feedback","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.01252","title":"MeRoPE: Metric Rotary Position Embedding for Camera-Controlled Video Generation","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.15018","title":"G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2501.09347","title":"UVRM: A Scalable 3D Reconstruction Model from Unposed Videos","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2507.18597","title":"Linear Memory SE(2) Invariant Attention","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2601.11772","title":"studentSplat: Your Student Model Learns Single-view 3D Gaussian Splatting","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.07533","title":"ACCURATE: Arbitrary-shaped Continuum Reconstruction Under Robust Adaptive Two-view Estimation","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.08096","title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.16016","title":"FlatLands: Generative Floormap Completion From a Single Egocentric View","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.23045","title":"A Differentiable Framework for Global Circulation Model Precipitation Bias Correction","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.30705","title":"Equivariant Latent Alignment via Flow Matching under Group Symmetries","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2606.01590","title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","created":"2026-06-01","cited_by_count":0,"area":"diffusion"},{"id":"2606.20547","title":"The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.02712","title":"Global Pose Control for Generative View Synthesis in Normalized Object Coordinate Space","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05348","title":"Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.12000","title":"MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.03824","title":"VI3: Grounding Pretrained 3D Foundation Models with Inertial Cues","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.07414","title":"RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.20106","title":"AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention","created":"2026-09-17","cited_by_count":0,"area":"alignment"},{"id":"2609.21212","title":"Visual Navigation Transformer with Pose Attention","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.03522","title":"Feedforward Novel View Synthesis for Heterogeneous Cameras","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06229","title":"SO(3)-RoPE for Spherical Transformers","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09785","title":"UltraWorld: Learning Interactive Ultrasound World Models from Untracked Clinical Videos with Acoustic Sampling Map","created":"2026-10-07","cited_by_count":0,"area":"wm"},{"id":"2610.16337","title":"WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19257","title":"Long-horizon Video Generation with Slot Memory Addressed By Region Tokens","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}