Search papers, labs, and topics across Lattice.
University of Surrey
3
0
7
Most ALMs fail to ground their audio deepfake detection rationales in actual acoustic evidence, despite generating plausible explanations.
CRIP selectively fuses features from clients based on representational similarity, leading to superior performance in one-shot federated learning under extreme domain heterogeneity.
Unbalanced class prevalence, not just disjoint label sets, is the dominant factor hindering federated learning performance under label-space heterogeneity.
