5 papers
Geometric Manifold Rectification for Imbalanced Learning
Xubin Wang, Qing Li, Weijia Jia
Imbalanced classification presents a formidable challenge in machine learning, particularly when tabular datasets are plagued by noise and overlapping class boundaries. From a geom…
Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning
Xubin Wang, Weijia Jia
Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples…
Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment
Xubin Wang, Qing Li, Weijia Jia
This article surveys Cognitive Edge Computing as a practical and methodical pathway for deploying reasoning-capable Large Language Models (LLMs) and autonomous AI agents on resourc…
Demonstration Selection for In-Context Learning via Reinforcement Learning
Xubin Wang, Jianfei Wu, Yichen Yuan +3
Diversity in demonstration selection is critical for enhancing model generalization by enabling broader coverage of structures and concepts. Constructing appropriate demonstration…
Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
Xubin Wang, Zhiqing Tang, Jianxiong Guo +4
The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the…