{"total":19,"rows":[{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134,"area":"wm"},{"id":"2404.05221","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","created":"2024-04-08","cited_by_count":70,"area":"wm"},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2605.10806","title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","created":"2026-05-11","cited_by_count":12,"area":"wm"},{"id":"2512.08029","title":"CLARITY: Medical World Model for Guiding Treatment Decisions by Simulating Context-Aware Disease Trajectories","created":"2025-12-08","cited_by_count":6,"area":"wm"},{"id":"2606.17800","title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","created":"2026-06-16","cited_by_count":6,"area":"wm"},{"id":"2608.27073","title":"SpatialCrafter: Single Image World Modeling with Generative 3D Proxies","created":"2026-08-27","cited_by_count":3,"area":"wm"},{"id":"2512.17992","title":"Unifying Deep Predicate Invention with Pre-trained Foundation Models","created":"2025-12-19","cited_by_count":2,"area":"wm"},{"id":"2607.28226","title":"Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2605.09355","title":"FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning","created":"2026-05-10","cited_by_count":1,"area":"wm"},{"id":"2606.28385","title":"RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis","created":"2026-06-22","cited_by_count":1,"area":"wm"},{"id":"2610.01614","title":"Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models","created":"2026-10-01","cited_by_count":1,"area":"wm"},{"id":"2602.01644","title":"From Perception to Action: Spatial AI Agents and World Models","created":"2026-02-02","cited_by_count":0,"area":"wm"},{"id":"2603.06687","title":"TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings","created":"2026-03-04","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":"2606.27806","title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","created":"2026-06-26","cited_by_count":0,"area":"wm"},{"id":"2607.18709","title":"RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation","created":"2026-07-21","cited_by_count":0,"area":"wm"},{"id":"2609.08342","title":"VeriScene: Reconstructing Crime Scenes from Legal Evidence via World-Model Agent","created":"2026-09-08","cited_by_count":0,"area":"wm"}],"next_cursor":null}