Just How Flexible are Neural Networks in Practice?by Ravid Shwartz-Ziv, Micah Goldblum, Arpit Bansal, C.…
Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Modelsby Lukas Thede, Karsten Roth,…
KernelWarehouse: Rethinking the Design of Dynamic Convolutionby Chao Li, Anbang YaoFirst submitted to arxiv on:…
SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Informationby Kaiye Zhou, Shucheng Wang, Jun XuFirst submitted…
Low-Rank Quantization-Aware Training for LLMsby Yelysei Bondarenko, Riccardo Del Chiaro, Markus NagelFirst submitted to arxiv…
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuningby Yibo Yang, Xiaojie…
Efficient Differentially Private Fine-Tuning of Diffusion Modelsby Jing Liu, Andrew Lowy, Toshiaki Koike-Akino, Kieran Parsons,…
Time Sensitive Knowledge Editing through Efficient Finetuningby Xiou Ge, Ali Mousavi, Edouard Grave, Armand Joulin,…
Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Needby Martin…
PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detectionby Ronghui Xu, Hao Miao, Senzhang…