mlsanityData to 14 Oct 2026

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

arXiv 2605.13651 ↗First posted 13 May 2026cs.SD cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 attention allocation as an auditory salience filtering problem. At its core is OWM, a neuro-inspired Oscillatory Working Memory that maintains stable attractor-like states and triggers higher-cognition ALM processing only when adaptive energy fluctuations signal perceptual salience, triggering higher-level reasoning. On XD-Violence, NAACA improves AudioQwen's average precision (AP) from 53.50% to 70.60% while reducing unnecessary ALM invocations. Furthermore, qualitative case studies on the Urban Soundscapes of the World (USoW) dataset show that OWM captures novel events and subcategory shifts while remaining robust to transient pauses and ambient urban noise.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 30 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

13 of 30 references.

References · 13

  1. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  2. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 574
  3. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 243
  4. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  5. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 229
  6. 2025Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reactioncited by 127
  7. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  8. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 70
  9. 2024Unsupervised Concept Drift Detection from Deep Learning Representations in Real-timecited by 16
  10. 2024Online Drift Detection with Maximum Concept Discrepancycited by 12
  11. 2025AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detectioncited by 7
  12. 2023AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learningcited by 2
1 more
  1. 2025TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detectioncited by 1

Built on by

Not cited yet.