$\mathcal{Y}$-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning. (arXiv:2202.09817v2 [cs.CL] UPDATED) Show more
http://arxiv.org/abs/2202.09817 #arXiv #NLProc
QOTO: Question Others to Teach Ourselves An inclusive, Academic Freedom, instance All cultures welcome. Hate speech and harassment strictly forbidden.