{"total":96,"rows":[{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134,"area":"vla"},{"id":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96,"area":"wm"},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2510.16732","title":"A Comprehensive Survey on World Models for Embodied AI","created":"2025-10-19","cited_by_count":68,"area":"wm"},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38,"area":"wm"},{"id":"2510.25616","title":"Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization","created":"2025-10-29","cited_by_count":35,"area":"mllm"},{"id":"2601.04090","title":"Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction","created":"2026-01-07","cited_by_count":31,"area":"diffusion"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24,"area":"diffusion"},{"id":"2604.18564","title":"MultiWorld: Scalable Multi-Agent Multi-View Video World Models","created":"2026-04-20","cited_by_count":23,"area":"wm"},{"id":"2603.16195","title":"S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight","created":"2026-03-17","cited_by_count":17,"area":null},{"id":"2602.03747","title":"LIVE: Long-horizon Interactive Video World Modeling","created":"2026-02-03","cited_by_count":16,"area":"wm"},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2603.14366","title":"Representation Alignment for Just Image Transformers is not Easier than You Think","created":"2026-03-15","cited_by_count":14,"area":"diffusion"},{"id":"2509.23958","title":"Reinforcement Learning with Inverse Rewards for World Model Post-training","created":"2025-09-28","cited_by_count":13,"area":"wm"},{"id":"2603.12655","title":"VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model","created":"2026-03-13","cited_by_count":13,"area":"wm"},{"id":"2606.02436","title":"Geometry-Aware Implicit Memory for Video World Models","created":"2026-06-01","cited_by_count":13,"area":"wm"},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12,"area":"wm"},{"id":"2604.06168","title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","created":"2026-04-07","cited_by_count":12,"area":"wm"},{"id":"2604.24764","title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","created":"2026-04-27","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":"2512.03045","title":"CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2605.22882","title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","created":"2026-05-20","cited_by_count":8,"area":"wm"},{"id":"2606.01164","title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","created":"2026-05-31","cited_by_count":8,"area":"wm"},{"id":"2602.06959","title":"CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2603.00466","title":"DreamWorld: Unified World Modeling in Video Generation","created":"2026-02-28","cited_by_count":7,"area":"wm"},{"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":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2509.12437","title":"Enhancing Physical Consistency in Lightweight World Models","created":"2025-09-15","cited_by_count":5,"area":"wm"},{"id":"2511.22815","title":"Captain Safari: A World Engine with Pose-Aligned 3D Memory","created":"2025-11-28","cited_by_count":5,"area":null},{"id":"2512.07821","title":"WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2512.19402","title":"Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2603.26193","title":"MemCam: Memory-Augmented Camera Control for Consistent Video Generation","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2604.04050","title":"TORA: Topological Representation Alignment for 3D Shape Assembly","created":"2026-04-05","cited_by_count":4,"area":"diffusion"},{"id":"2605.07079","title":"Learning Visual Feature-Based World Models via Residual Latent Action","created":"2026-05-08","cited_by_count":4,"area":"wm"},{"id":"2607.05373","title":"PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space","created":"2026-07-06","cited_by_count":4,"area":"diffusion"},{"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":"2603.14965","title":"GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis","created":"2026-03-16","cited_by_count":3,"area":"diffusion"},{"id":"2604.19636","title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","created":"2026-04-21","cited_by_count":3,"area":"diffusion"},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2608.26671","title":"RECAP-Forcing: Retaining Content Appearances for Long Video Generation","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2608.27073","title":"SpatialCrafter: Single Image World Modeling with Generative 3D Proxies","created":"2026-08-27","cited_by_count":3,"area":"wm"},{"id":"2602.03753","title":"Test-Time Conditioning with Representation-Aligned Visual Features","created":"2026-02-03","cited_by_count":2,"area":"diffusion"},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2605.18365","title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2605.19539","title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.24761","title":"Drift-Resistant Navigation World Model with Anchored Epipolar Guidance","created":"2026-05-23","cited_by_count":2,"area":"wm"},{"id":"2607.00712","title":"Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption","created":"2026-07-01","cited_by_count":2,"area":"inference"},{"id":"2608.30692","title":"Can Video World Models Track Unobserved World States?","created":"2026-08-31","cited_by_count":2,"area":"wm"},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.11367","title":"3D-Belief: Embodied Belief Inference via Generative 3D World Modeling","created":"2026-05-12","cited_by_count":1,"area":"wm"},{"id":"2605.24962","title":"Tempered Self-Similarity Alignment for Physically Plausible Video Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.10656","title":"Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.13345","title":"JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.27192","title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.19120","title":"Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models","created":"2026-07-21","cited_by_count":1,"area":"diffusion"},{"id":"2608.01127","title":"MiniWorld: Democratizing the Training of Video World Models from Scratch","created":"2026-08-02","cited_by_count":1,"area":"wm"},{"id":"2608.10107","title":"4D-WAM: 4D Consistent World Modeling for Autonomous Driving","created":"2026-08-10","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":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","cited_by_count":0,"area":"lr"},{"id":"2602.20079","title":"SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis","created":"2026-02-23","cited_by_count":0,"area":"diffusion"},{"id":"2603.05506","title":"FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.13357","title":"Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.16306","title":"DriveFix: Spatio-Temporally Coherent Driving Scene Restoration","created":"2026-03-17","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":"2605.30855","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":"2605.31466","title":"VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2606.04291","title":"A Cookbook of 3D Vision: Data, Learning Paradigms, and Application","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.28581","title":"ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.04633","title":"Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models","created":"2026-08-05","cited_by_count":0,"area":"vla"},{"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":"2608.17832","title":"GenRec: Knowing Where to Reconstruct and Where to Generate","created":"2026-08-18","cited_by_count":0,"area":"diffusion"},{"id":"2608.30643","title":"Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models","created":"2026-08-31","cited_by_count":0,"area":"vla"},{"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":"2609.03563","title":"FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.11548","title":"World in World: Explore the World with World Models","created":"2026-09-10","cited_by_count":0,"area":"wm"},{"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":"2609.33575","title":"SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models","created":"2026-09-27","cited_by_count":0,"area":"vla"},{"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":"2609.35292","title":"Scaffold Then Internalize: Representation Injection for Diffusion Transformers","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"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":"2609.37970","title":"PhysWAM: Physically Consistent World Action Model for Autonomous Driving","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2610.00483","title":"PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.01914","title":"DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04152","title":"Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution","created":"2026-10-02","cited_by_count":0,"area":"wm"},{"id":"2610.06687","title":"ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11174","title":"IntactWorld: Joint World Modeling with Intact Features","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.16558","title":"G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.18779","title":"GAD: Geometry Attention Distillation for Consistent Video Generation","created":"2026-10-13","cited_by_count":0,"area":"diffusion"},{"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":"2610.20111","title":"RepForcing: Representation-Space Initialization for Autoregressive Video Distillation","created":"2026-10-14","cited_by_count":0,"area":"diffusion"},{"id":"2610.20571","title":"Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}