Search papers, labs, and topics across Lattice.
Duke Kunshan University
2
0
6
Multimodal fusion can actually *hurt* performance in medical imaging tasks like predicting visual field loss, unless you carefully address data imbalance and modality conflict.
Robots can now catch dynamically moving objects with human-level dexterity, thanks to a shared autonomy framework that intelligently blends teleoperation with learned diffusion policies.
