y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#attention-sparsity News & Analysis

1 article tagged with #attention-sparsity. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AIBullisharXiv – CS AI · 7h ago6/10
🧠

MURMUR: An Efficient Inference System for Long-Form ASR

Researchers introduce Murmur, an inference system that optimizes long-form automatic speech recognition by balancing accuracy and latency through a two-level approach: intermediate chunk sizes at the inter-chunk level and attention sparsity exploitation at the intra-chunk level. The system achieves 4.2x latency reduction while maintaining single-pass accuracy on benchmark tests.