Search papers, labs, and topics across Lattice.
Xi’an Jiaotong University
2
0
6
0
Domain-specific knowledge hypergraphs can now be extracted with significantly improved quality by dynamically learning and applying extraction skills, outperforming static few-shot learning.
Weight regularization, often overlooked in parameter-efficient continual learning, can still significantly improve the stability-plasticity trade-off, even when using low-rank adapters.
