{"total":77,"rows":[{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154,"area":"wm"},{"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":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96,"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":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"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":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2606.16993","title":"DreamX-World 1.0: A General-Purpose Interactive World Model","created":"2026-06-15","cited_by_count":40,"area":"wm"},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2512.08931","title":"Astra: General Interactive World Model with Autoregressive Denoising","created":"2025-12-09","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":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28,"area":"wm"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2605.30263","title":"minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models","created":"2026-05-28","cited_by_count":19,"area":"wm"},{"id":"2606.00793","title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","created":"2026-05-30","cited_by_count":18,"area":"wm"},{"id":"2605.03941","title":"iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework","created":"2026-05-05","cited_by_count":14,"area":"wm"},{"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":"2604.04931","title":"LoMa: Local Feature Matching Revisited","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2607.18367","title":"AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report","created":"2026-07-20","cited_by_count":11,"area":"wm"},{"id":"2511.00108","title":"Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence","created":"2025-10-30","cited_by_count":10,"area":null},{"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":"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":"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":"2605.18748","title":"Aurora: Unified Video Editing with a Tool-Using Agent","created":"2026-05-18","cited_by_count":9,"area":"diffusion"},{"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":"2606.14162","title":"VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling","created":"2026-06-12","cited_by_count":7,"area":"diffusion"},{"id":"2606.23105","title":"Compression and Retrieval: Implicit Memory Retrieval for Video World Models","created":"2026-06-22","cited_by_count":6,"area":"wm"},{"id":"2511.18373","title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","created":"2025-11-23","cited_by_count":5,"area":"lr"},{"id":"2604.12251","title":"ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models","created":"2026-04-14","cited_by_count":5,"area":null},{"id":"2607.03964","title":"Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control","created":"2026-07-04","cited_by_count":5,"area":"wm"},{"id":"2605.05997","title":"4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding","created":"2026-05-07","cited_by_count":4,"area":"lr"},{"id":"2609.17909","title":"Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control","created":"2026-09-15","cited_by_count":4,"area":"wm"},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2603.13119","title":"Geometry-Guided Camera Motion Understanding in VideoLLMs","created":"2026-03-13","cited_by_count":3,"area":"mllm"},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"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":"2608.09449","title":"Sekai2: From World Exploration to Interactive World Modeling","created":"2026-08-10","cited_by_count":3,"area":"wm"},{"id":"2512.09112","title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2603.06445","title":"What if? Emulative Simulation with World Models for Situated Reasoning","created":"2026-03-06","cited_by_count":2,"area":"wm"},{"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":"2604.07990","title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.11809","title":"Who Handles Orientation? Investigating Invariance in Feature Matching","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.06658","title":"Relit-LiVE: Relight Video by Jointly Learning Environment Video","created":"2026-05-07","cited_by_count":1,"area":"diffusion"},{"id":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2606.11568","title":"4DP-QA: Scalable QA for 4D Perception in Vision Language Models","created":"2026-06-10","cited_by_count":1,"area":"mllm"},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","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":"2607.03043","title":"Natural Language Camera Movement Understanding","created":"2026-07-03","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":"2608.10932","title":"Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation","created":"2026-08-11","cited_by_count":1,"area":"distill"},{"id":"2609.03919","title":"OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping","created":"2026-09-03","cited_by_count":1,"area":"diffusion"},{"id":"2609.34470","title":"Precise Editing and Flexible Referencing for Interactable Worlds","created":"2026-09-28","cited_by_count":1,"area":"wm"},{"id":"2603.14733","title":"A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"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":"2605.07390","title":"ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation","created":"2026-05-08","cited_by_count":0,"area":"wm"},{"id":"2605.31535","title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.16449","title":"PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.17832","title":"GenRec: Knowing Where to Reconstruct and Where to Generate","created":"2026-08-18","cited_by_count":0,"area":"diffusion"},{"id":"2608.22039","title":"ORBIT++: Benchmarking SfM in the Wild with 360{\\deg} Video","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.29177","title":"Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.03557","title":"Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation","created":"2026-09-03","cited_by_count":0,"area":"wm"},{"id":"2609.09507","title":"RoMa-$\\Omega$: What Feed-Forward 3D Models Know About Image Matching","created":"2026-09-08","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":"2609.33935","title":"Unifying Video Tasks via Spatiotemporal Analogy","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35560","title":"WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.38077","title":"MUGEN: Interactive Panoramic World Exploration via Camera Control","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38146","title":"LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.39227","title":"Emergent Multi-View Geometry Through Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.13706","title":"GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.14679","title":"HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.17625","title":"4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling","created":"2026-10-13","cited_by_count":0,"area":"wm"},{"id":"2610.19726","title":"Generative World Simulation with DAO and JING","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20160","title":"OneLA: Learning Many Worlds from Latent Actions","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}