Search papers, labs, and topics across Lattice.
6
0
6
Over 1,100 submissions reveal groundbreaking advancements in sports video understanding, with new methods pushing the boundaries of action prediction and localization.
AETDICE resolves the long-standing divide in nonlinear multi-objective RL, enabling nuanced trade-off optimization that previous methods overlooked.
ACPO achieves joint policy optimization in MARL by enabling independent agent updates that effectively coordinate through a belief mechanism, outperforming traditional methods as agent numbers grow.
Motion-aware correspondences can drastically enhance the geometric consistency of novel-view video generation, outperforming traditional methods.
Learning policies from just one trajectory in average-reward MDPs is now feasible, with guarantees that could transform how we approach sample efficiency in reinforcement learning.
MORPHOS achieves unprecedented temporal consistency in 3D asset generation by leveraging a unified 4D representation that adapts to evolving topologies.
