Research map / Architectures and efficiency / Attention and transformers
NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
Zhongju Yuan, Geraint A. Wiggins, Dick B.M. Botteldooren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add OWM salience-driven gating | AudioQwen · XD-Violence test (audio) | AP (%): 53.50 -> 70.60 | Improved |
| gate with random 4 s segments (same count) instead of exhaustive inference (ablation) | AudioQwen · XD-Violence test (audio) | AP (%): 53.50 -> 60.44 | Improved |
| select segments with OWM instead of random 4 s segments (ablation) | NAACA · XD-Violence test (audio) | AP (%): 60.44 -> 70.60 | Improved |
| gate ALM invocations with OWM instead of exhaustive sliding windows | AudioQwen · XD-Violence and USoW | ALM invocations per clip: 57 -> 34 | Improved |
Closest papers by meaning
- RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark (NeurIPS 2026 · similarity 0.85)
- S$^2$M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection (NeurIPS 2025 · similarity 0.85)
- AND: Audio Network Dissection for Interpreting Deep Acoustic Models (ICML 2024 · similarity 0.84)
- SALMONN: Towards Generic Hearing Abilities for Large Language Models (ICLR 2024 · similarity 0.84)
- Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization (NeurIPS 2025 · similarity 0.84)
- Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
