Search papers, labs, and topics across Lattice.
Bohyung Han with Seoul National University and Washington Ramos
3
0
7
Kickstart MoE training by initializing experts with semantically meaningful subspaces, leading to faster specialization and better performance than standard upcycling techniques.
Distilling patch-text alignment knowledge from a teacher model to a student surprisingly *improves* the student's alignment beyond that of the teacher.
VLA models struggle with physical reasoning, but Pri4R's simple trick of predicting 3D point tracks during training boosts performance by up to 40% on manipulation tasks, without adding any inference overhead.
