Parameter-efficient fine-tuning (PEFT) methods adapt large models by introducing a small number of trainable parameters. However, we find that these parameters still contain redundancy and can be further compressed while maintaining strong task performance. To this end, we propose a novel hierarchical low-rank reparame...
Rong Huang, Yi Xiong, Yuan-Yuan Cheng et al.· 0 citations
This work proposes a novel source-prior-driven selective adaptation method to efficiently fine-tune diffusion models, achieving a favorable trade-off between adaptation-retention and generative capability.
Yi Xiong, Yuan-yuan Cheng, Xiao-Ming Fu· arXiv.org· 0 citations
This work proposes a label-free criterion that jointly selects the algorithm and hyperparameters for UDA, and achieves better selection performance than other methods and remains effective across different algorithm pools.
Yi Xiong, L. Gallée, D. Wolf et al.· arXiv.org· 0 citations
This study finds that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable.
Yi Xiong, L. Gallée, D. Wolf et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.