← Search

Yikai Liao

1 accepted papers

2025

CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

ICLR 2025poster

The emergence of the foundation model era has sparked immense research interest in utilizing pre-trained representations for continual learning~(CL), yielding a series of strong CL methods with outstanding performance on standard evaluation benchmarks. Nonetheless, there are growing concerns regardi…