{"total":50,"rows":[{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2601.18577","title":"Self-Refining Video Sampling","created":"2026-01-26","cited_by_count":15,"area":null},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2601.05239","title":"Plenoptic Video Generation","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2601.22301","title":"Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes","created":"2026-01-29","cited_by_count":9,"area":null},{"id":"2602.18742","title":"RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning","created":"2026-02-21","cited_by_count":8,"area":null},{"id":"2605.15153","title":"Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action","created":"2026-05-14","cited_by_count":8,"area":null},{"id":"2605.28230","title":"Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation","created":"2026-05-27","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2604.27621","title":"Robot Learning from Human Videos: A Survey","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2603.26546","title":"AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2604.11797","title":"SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2605.20290","title":"PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2608.15555","title":"RigidBench: Evaluating Rigid-Body Physics in Video Generation Models","created":"2026-08-16","cited_by_count":4,"area":null},{"id":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2512.17445","title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2602.00508","title":"DuoGen: Towards General Purpose Interleaved Multimodal Generation","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2603.16822","title":"Surg$\\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.01207","title":"TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2605.13790","title":"Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.25306","title":"Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation","created":"2026-06-24","cited_by_count":2,"area":null},{"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":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.10276","title":"Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction","created":"2026-06-09","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":"2606.20891","title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.29020","title":"Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.21848","title":"Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.07693","title":"CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2512.07720","title":"ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.07540","title":"Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.17565","title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.00050","title":"Learning physically grounded traffic accident reconstruction from public accident reports","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.15116","title":"DriveCtrl: Conditioned Sim-to-Real Driving Video Generation","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.27554","title":"Understanding Cross-Rig Generalization in Automotive Perception: a Multi-Rig Benchmark and Rig Variation Metrics","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.21628","title":"Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.22187","title":"BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.18077","title":"vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.36599","title":"Scaling Video Generation for Reasoning: At What Cost?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39601","title":"GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02197","title":"HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02580","title":"Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02825","title":"TerrainForge: Physics-Grounded Road Geometry Editing for Counterfactual Autonomous Driving","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.03664","title":"ProAR: Learning Prospective Reasoning with Autoregressive Video Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12374","title":"AgentGarten: Code Worlds for Evolving Agents","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14153","title":"TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.20124","title":"DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}