Dual Low-Rank Adaptation for Continual Learning with Pre-Trained Modelsby Huancheng Chen, Jingtao Li, Nidham Gazagnadou,…
Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Modelsby Donghoon Kim, Gusang…
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimationby Stefan Stojanovic, Yassir Jedra, Alexandre ProutiereFirst…
SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generationby Yining Hong, Beide Liu, Maxine Wu, Yuanhao…
Exploring Gradient Subspaces: Addressing and Overcoming LoRA’s Limitations in Federated Fine-Tuning of Large Language Modelsby…
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learningby Xujia Wang, Haiyan Zhao, Shuo…
Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clientsby Jabin Koo, Minwoo Jang, Jungseul…
CopRA: A Progressive LoRA Training Strategyby Zhan Zhuang, Xiequn Wang, Yulong Zhang, Wei Li, Yu…
LoRA vs Full Fine-tuning: An Illusion of Equivalenceby Reece Shuttleworth, Jacob Andreas, Antonio Torralba, Pratyusha…
Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devicesby Hiroki Matsutani, Masaaki Kondo,…