3 papers
cs.LG2025
Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
Runxi Cheng, Feng Xiong, Yongxian Wei +2
Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between…
cs.IT2025
CommGPT: A Graph and Retrieval-Augmented Multimodal Communication Foundation Model
Feibo Jiang, Wanyun Zhu, Li Dong +4
Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain…
cs.LG2024
Learn To Learn More Precisely
Runxi Cheng, Yongxian Wei, Xianglong He +5
Meta-learning has been extensively applied in the domains of few-shot learning and fast adaptation, achieving remarkable performance. While Meta-learning methods like Model-Agnosti…