Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferencesby Nikolaos Dimitriadis, Pascal Frossard, Francois FleuretFirst submitted…
ROSA: Random Subspace Adaptation for Efficient Fine-Tuningby Marawan Gamal Abdel Hameed, Aristides Milios, Siva Reddy,…
SBoRA: Low-Rank Adaptation with Regional Weight Updatesby Lai-Man Po, Yuyang Liu, Haoxuan Wu, Tianqi Zhang,…
See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decompositionby Chongjie Si,…
HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuningby Liyuan Wang, Jingyi Xie, Xingxing Zhang,…
LoRA-GA: Low-Rank Adaptation with Gradient Approximationby Shaowen Wang, Linxi Yu, Jian LiFirst submitted to arxiv…
GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuningby Aleksander Ficek, Jiaqi Zeng,…
Mixture of A Million Expertsby Xu Owen HeFirst submitted to arxiv on: 4 Jul 2024CategoriesMain:…
Multi-Convformer: Extending Conformer with Multiple Convolution Kernelsby Darshan Prabhu, Yifan Peng, Preethi Jyothi, Shinji WatanabeFirst…
LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Modelsby Hayder Elesedy, Pedro M.…