Publications (20)
Developing an aqueous approach for synthesizing Au and M@Au (M = Pd, CuPt) hybrid nanostars with plasmonic properties
Jingshan Du, Junjie Yu, Yalin Xiong +3
Anisotropic Au nanoparticles show unique localized surface plasmon resonance (LSPR) properties, which make it attractive in optical, sensing, and biomedical applications. In this c…
Understanding Generalization from Embedding Dimension and Distributional Convergence
Junjie Yu, Zhuoli Ouyang, Haotian Deng +5
Deep neural networks often generalize well despite heavy over-parameterization, challenging classical parameter-based analyses. We study generalization from a representation-centri…
Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration
Xudong Guo, Daming Shi, Junjie Yu +1
The emergence of multi-agent reinforcement learning (MARL) is significantly transforming various fields like autonomous vehicle networks. However, real-world multi-agent systems ty…
Embedding Decomposition for Artifacts Removal in EEG Signals
Junjie Yu, Chenyi Li, Kexin Lou +2
Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to eliminate or weaken the influence of artifacts. However, most of…
Scale-Invariance Drives Convergence in AI and Brain Representations
Junjie Yu, Wenxiao Ma, Jianyu Zhang +4
Despite variations in architecture and pretraining strategies, recent studies indicate that large-scale AI models often converge toward similar internal representations that also a…
Reinforcement Learning (RL) Meets Urban Climate Modeling: Investigating the Efficacy and Impacts of RL-Based HVAC Control
Junjie Yu, John S. Schreck, David John Gagne +7
Reinforcement learning (RL)-based heating, ventilation, and air conditioning (HVAC) control has emerged as a promising technology for reducing building energy consumption while mai…