PulseAugur
实时 15:31:39
English(EN) LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation

LiVeAction 神经编解码器为实时传感器提供高效、通用的压缩

研究人员开发了 LiVeAction,这是一种专为资源受限设备上的实时操作而设计的新型神经编解码器。该架构通过类似 FFT 的结构降低编码器复杂度,并用基于方差的速率惩罚取代对抗性损失,从而解决了现有编解码器的局限性。与当前的生成式分词器相比,所得系统提供了改进的失真率性能,使其适用于低功耗传感器和非传统数据模式。 AI

影响 能够为边缘设备和新型数据类型实现更高效的实时 AI 处理。

排序理由 该集群包含一篇详细介绍新型神经编解码器设计的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

LiVeAction 神经编解码器为实时传感器提供高效、通用的压缩

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Dan Jacobellis, Neeraja J. Yadwadkar ·

    LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation

    arXiv:2605.06628v1 Announce Type: cross Abstract: Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized codecs such as JPEG and MPEG achieve efficient trad…

  2. arXiv cs.LG TIER_1 English(EN) · Neeraja J. Yadwadkar ·

    LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation

    Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized codecs such as JPEG and MPEG achieve efficient trade-offs between bitrate and perceptual quality but …