activity
20242026
collaborators

7 papers

cs.LG2026

Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation

Kewei Li, Rongying Zhang, Xueli Wang +5

Token aggregation is a common bottleneck in models that map token representations to sample-level predictions, yet most pooling methods operate only in the original token domain. W…

cs.LG2025

HeFS: Helper-Enhanced Feature Selection via Pareto-Optimized Genetic Search

Yusi Fan, Tian Wang, Zhiying Yan +8

Feature selection is a combinatorial optimization problem that is NP-hard. Conventional approaches often employ heuristic or greedy strategies, which are prone to premature converg…

cs.LG2025

A transformer-BiGRU-based framework with data augmentation and confident learning for network intrusion detection

Jiale Zhang, Pengfei He, Fei Li +5

In today's fast-paced digital communication, the surge in network traffic data and frequency demands robust and precise network intrusion solutions. Conventional machine learning m…

cs.LG2025

MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework

Jianping Zhao, Qiong Zhou, Tian Wang +8

MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trai…

cs.LG2025

DeepSelective: Interpretable Prognosis Prediction via Feature Selection and Compression in EHR Data

Ruochi Zhang, Qian Yang, Xiaoyang Wang +10

The rapid accumulation of Electronic Health Records (EHRs) has transformed healthcare by providing valuable data that enhance clinical predictions and diagnoses. While conventional…

cs.CL2025

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms

Kewei Li, Yanwen Kong, Yiping Xu +4

Since the emergence of research on improving the length extrapolation capabilities of large language models in 2021, some studies have made modifications to the scaling factor in t…