Hu Zhang

Ditch the manual masks: a new diffusion model leverages video metadata to blindly restore corrupted video, outperforming previous mask-dependent approaches.

General-purpose vision-language models stumble when looking down from drones, but a new benchmark reveals that multi-task learning can substantially improve their aerial reasoning skills.

Quantifying and integrating map uncertainty—both positional and semantic—into trajectory prediction pipelines significantly boosts forecast accuracy, even when using existing baseline models.