HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds Paper • 2604.14268 • Published Apr 15 • 127
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling Paper • 2603.26610 • Published Mar 27 • 9
Think over Trajectories: Leveraging Video Generation to Reconstruct GPS Trajectories from Cellular Signaling Paper • 2603.26610 • Published Mar 27 • 9
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 • 92
The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization Paper • 2601.03227 • Published Jan 6 • 2 • 5
The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization Paper • 2601.03227 • Published Jan 6 • 2
Sleeping Agents 1 Audio Geo-Localization Game 🎵 1 Guess where audio was recorded by clicking on a world map
The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization Paper • 2601.03227 • Published Jan 6 • 2
Sleeping Agents 1 Audio Geo-Localization Game 🎵 1 Guess where audio was recorded by clicking on a world map
The Sonar Moment: Benchmarking Audio-Language Models in Audio Geo-Localization Paper • 2601.03227 • Published Jan 6 • 2
Sleeping Agents 1 Audio Geo-Localization Game 🎵 1 Guess where audio was recorded by clicking on a world map
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
Urban In-Context Learning: Bridging Pretraining and Inference through Masked Diffusion for Urban Profiling Paper • 2508.03042 • Published Aug 5, 2025
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