Yi-Xin Liu

Synthetic data alone can match real-world GAD performance, but unlocking further gains requires models that explicitly fuse topological and semantic evidence.

Block copolymer phase-field models now predict domain structure and phase behavior with over fivefold reduction in errors, matching SCFT accuracy for complex topologies.

Open-set GNNs silently break when graphs violate homophily, but synthesizing pseudo-unknown proxies along cross-class displacement vectors restores robust out-of-distribution detection on heterophilic topologies.