HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published 23 days ago • 118
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling Paper • 2603.26610 • Published Mar 27 • 9
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published Mar 24 • 91
The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization Paper • 2601.03227 • Published Jan 6 • 2
Eyes Will Shut: A Vision-Based Next GPS Location Prediction Model by Reinforcement Learning from Visual Map Feed Back Paper • 2507.18661 • Published Jul 23, 2025 • 2