2 papers
cs.CV2026
NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
Chuheng Chen, Xiaofei Zhou, Geyuan Zhang +1
Low-Rank Adaptation (LoRA) fusion enables the composition of subject and style representations for controllable generation without retraining. However, existing approaches primaril…
cs.CL2024
HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation
Geyuan Zhang, Xiaofei Zhou, Chuheng Chen
Fine-tuning pre-trained language models for downstream tasks has achieved impressive results in NLP. However, fine-tuning all parameters becomes impractical due to the rapidly incr…