Zhen Tang

Zhen Tang, Ameer Hamoodi, Stevie Foglia et al.

This research addresses a validated TMS EEG cleaning pipeline and a corresponding benchmark dataset. It evaluates two widely used artifact removal pipelines. A reference dataset of carefully preprocessed EEG signals was established to support future algorithm development and enable systematic comparison of automated artifact removal strategies, despite the absence of a true physiological ground truth. The study evaluates the effectiveness of two widely used source based artifact removal approaches and examines their impact on signal quality improvement and preservation of TMS-evoked potentials. The results support the robustness of the proposed preprocessing workflow and demonstrate its potential for improving data reliability in both research and clinical applications. A key goal is integrating TMS EEG and embedding it within a larger BCI framework. Ultimately, these efforts aim to enhance understanding of cortical dynamics and expand the clinical and research applications of TMS EEG.

Shangqian Gao, Ting Hua, Reza Shirkavand et al.

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained devices or efficiently serving them. Prior approaches have attempted to alleviate these problems by permanently removing less important model structures, yet these methods often result in substantial performance degradation due to the permanent deletion of model parameters. In this work, we tried to mitigate this issue by reducing the number of active parameters without permanently removing them. Specifically, we introduce a differentiable dynamic pruning method that pushes dense models to maintain a fixed number of active parameters by converting their MLP layers into a Mixture of Experts (MoE) architecture. Our method, even without fine-tuning, consistently outperforms previous structural pruning techniques across diverse model families, including Phi-2, LLaMA-2, LLaMA-3, and Qwen-2.5.

Aarti Jajoo, Matthew Nicol, Jaime Gateno et al.

It is difficult to estimate the midsagittal plane of human subjects with craniomaxillofacial (CMF) deformities. We have developed a LAndmark GEometric Routine (LAGER), which automatically estimates a midsagittal plane for such subjects. The LAGER algorithm was based on the assumption that the optimal midsagittal plane of a patient with a deformity is the premorbid midsagittal plane of the patient (i.e. hypothetically normal without deformity). The LAGER algorithm consists of three steps. The first step quantifies the asymmetry of the landmarks using a Euclidean distance matrix analysis and ranks the landmarks according to their degree of asymmetry. The second step uses a recursive algorithm to drop outlier landmarks. The third step inputs the remaining landmarks into an optimization algorithm to determine an optimal midsaggital plane. We validate LAGER on 20 synthetic models mimicking the skulls of real patients with CMF deformities. The results indicated that all the LAGER algorithm-generated midsagittal planes met clinical criteria. Thus it can be used clinically to determine the midsagittal plane for patients with CMF deformities.