Two Heads Are Better than One: Distilling Large Language Model Features into Small Models with Feature Decomposition and Mixture
Lists
Only you see this
BibTeX
@inproceedings{fu2026two,
author = {Tianhao Fu and Xinxin Xu and Weichen Xu and Jue Chen and Ruilong Ren and Bowen Deng and Xinyu Zhao and Jian Cao and Xixin Cao},
title = {{Two Heads Are Better than One: Distilling Large Language Model Features into Small Models with Feature Decomposition and Mixture}},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2026},
doi = {10.1609/aaai.v40i23.38981},
}Loading related content...