English(EN) Preference-Aware Pareto Steering for Multi-Task Speech LLMs

新方法EA-SURF优化多任务语音大语言模型

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

研究人员开发了一种名为EA-SURF（Endpoint-Anchored Preference-Aware Sampling Uniformly along the Pareto Front）的新方法，以更好地管理多任务语音大语言模型中的任务权衡。该方法在联合训练期间调整标量化权重，以使模型的性能与特定的部署偏好保持一致。EA-SURF旨在改善由此产生的任务权衡，并在实验中显示，与标准的固定损失加权相比，归一化超体积增加了17.8%。 AI

影响该方法有望为各种应用带来更高效、更符合偏好的语音大语言模型。

排序理由该集群包含一篇关于语音大语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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; 该集群包含一篇关于语音大语言模型新方法的学术论文。[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: 16 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.CL TIER_1 English(EN) · Liuyuan Jiang, Vishal Sunder, Samuel Thomas, Brian Kingsbury, Jeff Kuo, Lisha Chen, George Saon · 2026-10-21 04:00

面向多任务语音大模型的偏好感知帕累托引导

arXiv:2610.27200v1 Announce Type: new Abstract: Speech large language models (LLMs) perform multiple tasks, including automatic speech recognition (ASR), timestamp prediction (TS), and speech translation (ST). Joint training of speech LLMs creates task trade-offs, yet standard tr…

本文如何被排名

报道来源 [1]

面向多任务语音大模型的偏好感知帕累托引导

相关实体

相关话题