Guang Zeng

Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective

2025 · arXiv (Cornell University)

Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation under distribution shifts. Existing graph OOD methods tend to follow the basic ideas of …

A High-Performance and Reconfigurable Hardware Architecture for FrodoKEM

2026 · IACR Transactions on Cryptographic Hardware and Embedded Systems

FrodoKEM is an unstructured lattice-based post-quantum key encapsulation mechanism (KEM) renowned for its minimal algebraic structure and conservative security guarantees, offering strong confidence in long-term security. Building on these characteristics, the scheme is on track …