4 papers · 1 filter
SaMA: Morpho Adaptation via Asymmetric Expansion of Kronecker Product
An Nguyen, Anh Tong
Low-rank adaptation (LoRA) has attracted significant attention in the parameter-efficient fine-tuning (PEFT) landscape. However, its design suffers from two fundamental limitations…
LoCO: Low-rank Compositional Rotation Fine-tuning
An Nguyen, Jaesik Choi, Anh Tong
Parameter-efficient fine-tuning (PEFT) has emerged as an critical technique for adapting large-scale foundation models across natural language processing and computer vision. While…
Quasi-Equivariant Metanetworks
Viet-Hoang Tran, An Nguyen, Benoît Guérand +2
Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serves only as a proxy for the un…
Monomial Matrix Group Equivariant Neural Functional Networks
Viet-Hoang Tran, Thieu N. Vo, Tho H. Tran +2
Neural functional networks (NFNs) have recently gained significant attention due to their diverse applications, ranging from predicting network generalization and network editing t…