Zhongju Yuan — accepted AI-conference papers

2026

NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating

Zhongju Yuan, Geraint Wiggins, Dick Botteldooren

ICML 2026poster

Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free NeuroAuditory Attentive Cognitive Architecture that reframes…

Cited by 0 Source ↗Scholar ↗

2025

BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics

Zhongju Yuan, Geraint A. Wiggins, Dick B.M. Botteldooren

NeurIPS 2025poster

Today’s deep learning architectures are primarily based on perceptron models, which do not capture the oscillatory dynamics characteristic of biological neurons. Although oscillatory systems have recently gained attention for their closer resemblance to neural behavior, they still fall short of mode…

Cited by 0 Source ↗Scholar ↗