Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
13
DreamHand achieves a groundbreaking 40% reduction in error for 3D hand trajectory recovery in occluded environments, setting a new standard for egocentric video analysis.
Stochastic negative sampling in Direct Preference Optimization (DPO) dramatically boosts recommendation accuracy, suggesting that carefully curated "wrong" answers are key to preference learning.
