Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging
"任务向量" 相关文章
On the Representations of Entities in Auto-regressive Large Language Models
Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
On Task Vectors and Gradients
用任务向量做模型编辑为何有效？这篇ICLR 2025 Oral论文给出了理论分析
UC Berkeley Researchers Explore the Role of Task Vectors in Vision-Language Models
