English(EN) PW-Pruning: Phase-Aware Expert Selection for Speech-Centric Omni-Modal Models

PW-Pruning 方法增强了面向语音的全模态模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了一种新颖的 PW-Pruning 方法，用于选择面向语音的全模态模型中的专家，以在保持性能的同时降低计算负载。这种阶段感知技术为不同的处理阶段构建了独立的权重重要性核，从而在 MMAU-mini 和 MMSU 等基准测试中显著提高了准确性。PW-Pruning 在 Qwen3-Omni 上展示了收益，并在 Qwen3.5-Omni 和 Nemotron 上提供了补充证据，表明语义阶段信息对于这些增强至关重要。 AI

影响引入了一种优化大型全模态模型的方法，有望降低语音和文本处理的计算成本。

排序理由详细介绍一种新的模型剪枝技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新的模型剪枝技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 4 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Junjie Cao, Fengping Tian, Wenjie Zhou, Xuanfan Ni, Chenyang Lyu, Siyou Liu, Longyue Wang, Weihua Luo · 2026-10-21 04:00

PW-Pruning：面向语音中心全模态模型的阶段感知专家选择

arXiv:2610.26891v1 Announce Type: cross Abstract: Sparse routing reduces per-token computation but leaves the full expert bank resident in memory. We study expert pruning for speech-centric omni-modal models, where pooling calibration statistics can obscure the different expert d…

本文如何被排名

报道来源 [1]

PW-Pruning：面向语音中心全模态模型的阶段感知专家选择

相关实体

相关话题