Author name cluster

Min Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

54 papers

2 author rows

AAAI Conference 2026 Conference Paper

A Unified Shape-Aware Foundation Model for Time Series Classification

Zhen Liu
Yucheng Wang
Boyuan Li
Junhao Zheng
Emadeldeen Eldele
Min Wu
Qianli Ma

Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

PDF Details DOI

EAAI Journal 2026 Journal Article

Autoencoder: An efficient inverse design method for gallium nitride high electron mobility transistor structures

Yan Pang
Meilan Hao
Shu Wei
Lina Yu
Jufeng Han
Min Wu
Hong Qin
Weijun Li

Autoencoders are artificial neural networks widely used for feature extraction and data reconstruction, and can also be leveraged for device and material structure design. In gallium nitride (GaN) high electron mobility transistor (HEMT) inverse design, the mapping from target radio-frequency (RF) metrics to geometric parameters is often non-unique, meaning that multiple distinct structures can achieve similar performance. This one-to-many nature makes deterministic inverse regression unstable. Motivated by this challenge, this paper presents an autoencoder-based inverse design approach for GaN HEMT structures that learns the relationship between device geometry and two key RF metrics: cut-off frequency ( f T ) and maximum oscillation frequency ( f max ). The proposed method enables efficient generation of candidate GaN HEMT designs that match specified RF targets, using technology computer-aided design (TCAD) simulations to generate and label the training data. The model predicts four structural parameters, including gate–source spacing, gate length, gate field-plate length, and passivation-layer thickness. Experimental results show that the proposed framework can reliably generate structures consistent with the target specifications. The average relative error is 2. 64% for f T and 2. 67% for f max. Compared with direct inverse regression baselines, the autoencoder-based framework exhibits more stable training behavior and alleviates slow convergence or training failures caused by the non-uniqueness of the inverse mapping. In our implementation, the method can generate a candidate structure for a given RF target within a few milliseconds (ms), substantially reducing computational cost and providing an effective route to accelerate GaN HEMT device design.