{"total":57,"rows":[{"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":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23,"area":null},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15,"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":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"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":"2512.08269","title":"EgoX: Egocentric Video Generation from a Single Exocentric Video","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2602.21929","title":"Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2512.07806","title":"Multi-view Pyramid Transformer: Look Coarser to See Broader","created":"2025-12-08","cited_by_count":7,"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":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","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":"2601.05116","title":"From Rays to Projections: Better Inputs for Feed-Forward View Synthesis","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","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":"2605.15182","title":"Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2509.16132","title":"Recovering Parametric Scenes from Very Few Time-of-Flight Pixels","created":"2025-09-19","cited_by_count":3,"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":"2605.29891","title":"DVSM: Decoder-only View Synthesis Model Done Right","created":"2026-05-28","cited_by_count":2,"area":null},{"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":"2608.20534","title":"Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2605.10239","title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.22835","title":"OrthoMotion:Disentangling Camera and Subject Motion via Geometry Semantics Orthogonal Attention","created":"2026-06-22","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":"2607.02711","title":"RayTun3R: Online Camera Adaptation in 3D Foundation Models","created":"2026-07-02","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":"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":"2512.12898","title":"Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2603.12764","title":"SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.14302","title":"Geometrically Consistent Multi-View Scene Generation from Freehand Sketches","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.14760","title":"GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.30045","title":"Walking in the Implicit: Interactive World Exploration via Neural Scene Representation","created":"2026-06-29","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":"2607.12000","title":"MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.18593","title":"ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.28895","title":"ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views","created":"2026-08-28","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":"2609.21212","title":"Visual Navigation Transformer with Pose Attention","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.30056","title":"M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.34722","title":"Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35704","title":"DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38755","title":"Agentic Relative Camera Pose Estimation via Learned Ranking and Verification","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03308","title":"T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images","created":"2026-10-02","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":"2610.03717","title":"Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04722","title":"NAMVIS: Next-Scale Autoregressive Multi-View Image Synthesis","created":"2026-10-03","cited_by_count":0,"area":null},{"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}