{"total":67,"rows":[{"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":"2511.23429","title":"Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model","created":"2025-11-28","cited_by_count":61,"area":"wm"},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44,"area":"wm"},{"id":"2603.24581","title":"Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving","created":"2026-03-25","cited_by_count":33,"area":"wm"},{"id":"2601.05138","title":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","created":"2026-01-08","cited_by_count":28,"area":"wm"},{"id":"2602.09022","title":"WorldCompass: Reinforcement Learning for Long-Horizon World Models","created":"2026-02-09","cited_by_count":24,"area":"wm"},{"id":"2603.02049","title":"WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories","created":"2026-03-02","cited_by_count":18,"area":"diffusion"},{"id":"2512.18692","title":"EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images","created":"2025-12-21","cited_by_count":10,"area":null},{"id":"2602.22960","title":"UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models","created":"2026-02-26","cited_by_count":9,"area":"wm"},{"id":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2604.07053","title":"AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2512.16924","title":"The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2512.21003","title":"MVInverse: Feed-forward Multi-view Inverse Rendering in Seconds","created":"2025-12-24","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":"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":"2512.08930","title":"Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2602.02402","title":"SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2605.30115","title":"Large Depth Completion Model from Sparse Observations","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2607.10840","title":"OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields","created":"2026-07-12","cited_by_count":4,"area":"wm"},{"id":"2511.23191","title":"GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2512.08905","title":"Self-Evolving 3D Scene Generation from a Single Image","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2601.09697","title":"Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering","created":"2026-01-14","cited_by_count":3,"area":"diffusion"},{"id":"2602.01630","title":"Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2603.27222","title":"HD-VGGT: High-Resolution Visual Geometry Transformer","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2604.04707","title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","created":"2026-04-06","cited_by_count":3,"area":"wm"},{"id":"2606.20083","title":"Holo-World: Unified Camera, Object and Weather Control for Video World Model","created":"2026-06-18","cited_by_count":3,"area":"wm"},{"id":"2603.15433","title":"Real-Time Human Frontal View Synthesis from a Single Image","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.07287","title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2609.23753","title":"OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling","created":"2026-09-20","cited_by_count":2,"area":"wm"},{"id":"2512.17796","title":"CustomX: Unified Character, Action, and Scene Customization in Video World Models","created":"2025-12-18","cited_by_count":1,"area":"wm"},{"id":"2603.25129","title":"AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.15760","title":"Learn2Splat: Extending the Horizon of Learned 3DGS Optimization","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.16258","title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.22581","title":"SceneAligner: 3D-Grounded Floorplan Localization in the Wild","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.03254","title":"OF$^3$GS: On-the-Fly Feed-Forward 3D Gaussian Splatting from Unposed Images","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.30047","title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2606.30576","title":"Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.02301","title":"InvSplat: Inverse Feed-Forward Scene Splatting","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.11673","title":"ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space","created":"2026-07-13","cited_by_count":1,"area":"wm"},{"id":"2608.06827","title":"R2S-EGO: Dual-Proxy Refinement for Sparse-Capture Real-to-Sim","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.28288","title":"GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping","created":"2026-08-28","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":"2512.20927","title":"Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.17866","title":"MV-SAM: Multi-view Promptable Segmentation using Pointmap Guidance","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.27084","title":"SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.09688","title":"ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes","created":"2026-05-10","cited_by_count":0,"area":"diffusion"},{"id":"2605.19656","title":"Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.21131","title":"UniT: Unified Geometry Learning with Group Autoregressive Transformer","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27367","title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","created":"2026-05-26","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":"2608.07937","title":"FlexSplat: Flexible Feed-Forward 3D Gaussian Splatting without Point Cloud Correspondence","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.07987","title":"Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.16863","title":"SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.02847","title":"RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03952","title":"WorldReward: Reward Modeling for Camera-Conditioned World Models","created":"2026-09-03","cited_by_count":0,"area":"wm"},{"id":"2609.04174","title":"Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.20623","title":"PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructions","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.34579","title":"GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35734","title":"GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38592","title":"StereoGaussians: Feed-Forward 3D Gaussian Splatting from Stereo Images","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04351","title":"LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07958","title":"DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.12727","title":"Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.19708","title":"SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space","created":"2026-10-14","cited_by_count":0,"area":"wm"},{"id":"2610.20341","title":"InfiniSplat v2: Analyzing and Improving Feed-Forward 3DGS from Any Views","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}