Z Li's picture

Z Li

csroyli

·

csroyli

AI & ML interests

None yet

Recent Activity

repliedto SeanLee97's post about 11 hours ago

Our lab recently released a paper where we introduce ShadowPEFT, a new Parameter-Efficient Fine-Tuning (PEFT) paradigm tailored for edge computing scenarios. Unlike traditional approaches such as LoRA and its variants, which inject trainable parameters directly into the weights of Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing. - HF Paper: https://huggingface.co/papers/2604.19254 - GitHub: https://github.com/ShadowLLM/shadow-peft - HF Collection: https://huggingface.co/collections/shadow-llm/shadow-peft-models

commentedon a paper about 11 hours ago

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

commentedon a paper 1 day ago

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

View all activity

Organizations

Papers 5

arxiv:2604.19254

arxiv:2502.01523

arxiv:2402.14776

arxiv:2310.01208

models 0

None public yet

datasets 0

None public yet