{"total":17,"rows":[{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268,"area":"wm"},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2406.10429","title":"Consistency-diversity-realism Pareto fronts of conditional image generative models","created":"2024-06-14","cited_by_count":36,"area":"wm"},{"id":"2512.02793","title":"IC-World: In-Context Generation for Shared World Modeling","created":"2025-12-01","cited_by_count":6,"area":"wm"},{"id":"2503.08122","title":"Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments","created":"2025-03-11","cited_by_count":5,"area":"wm"},{"id":"2606.16519","title":"BadWorld: Adversarial Attacks on World Models","created":"2026-06-15","cited_by_count":5,"area":"wm"},{"id":"2511.17481","title":"Counterfactual World Models via Digital Twin-conditioned Video Diffusion","created":"2025-11-21","cited_by_count":4,"area":"wm"},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2604.09535","title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","created":"2026-04-10","cited_by_count":3,"area":"wm"},{"id":"2605.17916","title":"PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis","created":"2026-05-18","cited_by_count":3,"area":"wm"},{"id":"2603.19708","title":"WorldAgents: Can Foundation Image Models be Agents for 3D World Models?","created":"2026-03-20","cited_by_count":2,"area":"wm"},{"id":"2506.17967","title":"Adapting Vision-Language Models for Evaluating World Models","created":"2025-06-22","cited_by_count":1,"area":"wm"},{"id":"2605.05187","title":"LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)","created":"2026-05-06","cited_by_count":1,"area":"wm"},{"id":"2604.07758","title":"DailyArt: Discovering Articulation from Single Static Images via Latent Dynamics","created":"2026-04-09","cited_by_count":0,"area":"wm"},{"id":"2604.11386","title":"ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation","created":"2026-04-13","cited_by_count":0,"area":"wm"},{"id":"2607.00310","title":"RetailSMV: Exocentric vs. Egocentric Adaptation of Foundation Video World Models in Retail","created":"2026-07-01","cited_by_count":0,"area":"wm"},{"id":"2610.19063","title":"WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models","created":"2026-10-13","cited_by_count":0,"area":"wm"}],"next_cursor":null}