SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery Paper • 2609.31507 • Published Sep 25 • 6
WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning Paper • 2609.34826 • Published Sep 28 • 12
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks Paper • 2609.18805 • Published Sep 16 • 58