PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patchesby Rana Muhammad Shahroz…
Is Parameter Collision Hindering Continual Learning in LLMs?by Shuo Yang, Kun-Peng Ning, Yu-Yang Liu, Jia-Yu…
Fed-piLot: Optimizing LoRA Assignment for Efficient Federated Foundation Model Fine-Tuningby Zikai Zhang, Jiahao Xu, Ping…
LoLCATs: On Low-Rank Linearizing of Large Language Modelsby Michael Zhang, Simran Arora, Rahul Chalamala, Alan…
Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learningby Pengfei Jin, Peng Shu,…
AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Modelby Yuchen Li, Li Zhang, Youwei…
ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flawsby Hai Huang, Randall BalestrieroFirst submitted to arxiv…
MTL-LoRA: Low-Rank Adaptation for Multi-Task Learningby Yaming Yang, Dilxat Muhtar, Yelong Shen, Yuefeng Zhan, Jianfeng…
Parameter-Efficient Fine-Tuning via Selective Discrete Cosine Transformby Yixian Shen, Qi Bi, Jia-Hong Huang, Hongyi Zhu,…
Parameter-Efficient Fine-Tuning of State Space Modelsby Kevin Galim, Wonjun Kang, Yuchen Zeng, Hyung Il Koo,…