{"total":62,"rows":[{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100,"area":"wm"},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2601.02358","title":"VINO: A Unified Visual Generator with Interleaved OmniModal Context","created":"2026-01-05","cited_by_count":26,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2603.23497","title":"WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG","created":"2026-03-24","cited_by_count":13,"area":"wm"},{"id":"2609.02886","title":"SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models","created":"2026-09-02","cited_by_count":12,"area":"wm"},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2604.03723","title":"SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation","created":"2026-04-04","cited_by_count":10,"area":null},{"id":"2608.23565","title":"ReWorld: An Interactive World Model with Long-Horizon Memory","created":"2026-08-24","cited_by_count":10,"area":"wm"},{"id":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9,"area":"wm"},{"id":"2602.20157","title":"Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning","created":"2026-02-23","cited_by_count":9,"area":null},{"id":"2603.05078","title":"MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2606.31734","title":"MemLearner: Learning to Query Context memory for Video World Models","created":"2026-06-30","cited_by_count":9,"area":"wm"},{"id":"2511.18922","title":"One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control","created":"2025-11-24","cited_by_count":8,"area":null},{"id":"2602.14021","title":"Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow","created":"2026-02-15","cited_by_count":8,"area":null},{"id":"2607.02515","title":"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation","created":"2026-07-02","cited_by_count":7,"area":"diffusion"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2604.08532","title":"Self-Improving 4D Perception via Self-Distillation","created":"2026-04-09","cited_by_count":4,"area":"distill"},{"id":"2607.09225","title":"Glob3R: Global Structure-from-Motion with 3D Foundation Models","created":"2026-07-10","cited_by_count":4,"area":"wm"},{"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":"2607.14076","title":"From Pixels to States: Rethinking Interactive World Models as Game Engines","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2602.04441","title":"SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking","created":"2026-02-04","cited_by_count":3,"area":"synth"},{"id":"2602.08961","title":"MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2608.09449","title":"Sekai2: From World Exploration to Interactive World Modeling","created":"2026-08-10","cited_by_count":3,"area":"wm"},{"id":"2605.25077","title":"WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models","created":"2026-05-24","cited_by_count":2,"area":"wm"},{"id":"2605.26519","title":"$R^3$: 3D Reconstruction via Relative Regression","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2606.02552","title":"Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.07967","title":"DisCo: World Models with Discrete Camera Motion Control","created":"2026-06-06","cited_by_count":2,"area":"wm"},{"id":"2608.15659","title":"WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2609.09123","title":"Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout","created":"2026-09-08","cited_by_count":2,"area":"diffusion"},{"id":"2603.15614","title":"Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion","created":"2026-03-16","cited_by_count":1,"area":"diffusion"},{"id":"2605.12774","title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.27325","title":"Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model","created":"2026-06-25","cited_by_count":1,"area":"wm"},{"id":"2607.03789","title":"G$^2$TAM: Geometry Grounded Track Anything Model","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.05070","title":"HelloWorld: Enabling Socially Interactive Characters in Video World Models","created":"2026-08-05","cited_by_count":1,"area":"wm"},{"id":"2608.27529","title":"Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.09145","title":"Point4D: Long-range 4D Motion Reconstruction","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.09394","title":"OmniPoint: Universal Monocular Metric Pointcloud from Any Camera","created":"2026-09-08","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":"2609.34470","title":"Precise Editing and Flexible Referencing for Interactable Worlds","created":"2026-09-28","cited_by_count":1,"area":"wm"},{"id":"2603.23246","title":"GO-Renderer: Generative Object Rendering with 3D-aware Controllable Video Diffusion Models","created":"2026-03-24","cited_by_count":0,"area":"diffusion"},{"id":"2605.01896","title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","created":"2026-05-03","cited_by_count":0,"area":"wm"},{"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":"2605.30855","title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.01677","title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","created":"2026-07-02","cited_by_count":0,"area":"diffusion"},{"id":"2607.14419","title":"HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.24981","title":"GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.35023","title":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","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":"2610.14698","title":"PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18779","title":"GAD: Geometry Attention Distillation for Consistent Video Generation","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}