Kavli Affiliate: Jing Wang | First 5 Authors: Fu Feng, Jing Wang, Xin Geng, , | Summary: The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary, which may lead to negative transfer. In […]
Continue.. Transferring Core Knowledge via Learngenes