Search papers, labs, and topics across Lattice.
3
0
6
Monolithic federated updates are a fundamental bottleneck for embodied AI: decoupling vision, language, and action streams cuts uplink payloads by 96% and beats standard FedAvg by 22 percentage points under real-world wireless interference.
Amnesia reveals that controlling replay indices can stealthily degrade continual learning models while remaining largely undetected by standard audit mechanisms.
Spectral analysis of graph neighborhoods reveals a surprisingly effective and efficient way to boost anomaly detection, consistently outperforming existing GNN-based methods.
