Lei Zhu

Reform of state monitoring system for emergency diesel engine in nuclear power station

2018 · IOP Conference Series Materials Science and Engineering

An emergency diesel engine is installed at the nuclear power plant to cope with the power failure. In the case of accident, the diesel generator must be able to start quickly and reach the rated …

DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification

2023 · arXiv (Cornell University)

Diffusion Probabilistic Models have recently shown remarkable performance in generative image modeling, attracting significant attention in the computer vision community. However, while a substantial amount of diffusion-based research has focused on generative tasks, few studies …

EPA: Neural Collapse Inspired Robust Out-of-distribution Detector

2024

Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks. Existing works have leveraged the fact that In-distribution (ID) samples form a subspace in the feature space, achieving state-of-the-art (SOTA) performance. …

Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective

2025 · arXiv (Cornell University)

Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation under distribution shifts. Existing graph OOD methods tend to follow the basic ideas of …

Aspect-Aware Latent Factor Model

2018

Although latent factor models (e.g., matrix factorization) achieve good accuracy in rating prediction, they suffer from several problems including cold-start, non-transparency, and suboptimal recommendation for local users or items. In this paper, we employ textual …

A^3NCF: An Adaptive Aspect Attention Model for Rating Prediction

2018

Current recommender systems consider the various aspects of items for making accurate recommendations. Different users place different importance to these aspects which can be thought of as a preference/attention weight vector. Most existing recommender systems …

Interest-aware Message-Passing GCN for Recommendation

2021

Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order neighbors. Like other GCN models, …