Youfang Lin

FedTopo transforms federated learning by enabling reliable knowledge sharing through class relation topology, outperforming traditional methods in heterogeneous settings.

Agents trained with T2RD can generalize learned policies across environments without overfitting to irrelevant features, achieving state-of-the-art performance in VRL tasks.

Local motion representations can drastically improve reinforcement learning efficiency and transferability across diverse tasks, challenging the conventional global modeling approach.

Temporal correlations in video data can unlock a new level of sample efficiency and performance in Reinforcement Learning pre-training.