Zhiming Xu

TAILS resolves cross-task ambiguities in continual learning by directly correcting feature representations, leading to significant performance boosts without changing the underlying model.

SAMBA achieves state-of-the-art performance in SAR target recognition with fewer parameters by harnessing the unique scattering properties of SAR imagery.

KinematicRL bridges the sim-to-real gap in social navigation by leveraging higher-order control and a streamlined human tracking system, yielding robust real-world performance.

Learning dynamics through outcomes rather than parameters leads to significantly more robust policy adaptation in the face of real-world changes.