NAPE: Self-Supervised Audio Learning via Patch Prediction
ImperialCollegeLondon · hf · 2026-08-21
Imperial College London introduces NAPE (Listening Forward), a method using causal Transformers to predict successive spectrogram patch embeddings for scalable self-supervised audio learning without auxiliary components.
More from Research
- View: Pretraining Far From Saturated; Scale Not Necessary for Peak Intelligence — kalomaze · 2026-08-21
- MIT Lab Hiring Postdoc: Focus on Agentic AI and Multi-Agent Systems — GioeleZardini · 2026-08-21
- Experimental reward models locate worst-scored Gemma SFT outputs — kalomaze · 2026-08-21
- Brown U's Serena Booth to talk on soliciting human preferences — danielequercia · 2026-08-21
- NARU: Benchmark for Narrative Evolution in Japanese Long Video — utokyo-ai · 2026-08-21
- EMNLP Acceptance Rate Hits 15-Year Low, Blurring Track Distinctions — danish037 · 2026-08-21