Italiano(IT) OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion

OmniFusion 将多模态模型与 LLM 融合以实现同步翻译

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 04:00

研究人员开发了 OmniFusion，一种新颖的同步多语言多模态翻译方法。该方法将预训练的多模态基础模型 (MMFMs) 与专用的翻译大型语言模型 (LLMs) 融合，创建一个端到端系统。OmniFusion 使用 Omni 2.5-7B 作为 MMFM，SeedX PPO-7B 作为翻译 LLM 构建，可以处理语音到文本、语音和图像到文本以及文本和图像到文本的翻译。实验表明，与级联流水线相比，它将同步语音翻译的延迟减少了一秒，并通过有效利用音频和视觉输入提高了整体翻译质量。 AI

影响通过整合视觉和音频数据，实现更高效、更具上下文感知能力的翻译，有可能改善跨语言的实时通信。

排序理由该集群包含一篇详细介绍多模态翻译新模型和方法的论文。[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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍多模态翻译新模型和方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 Italiano(IT) · Sai Koneru, Matthias Huck, Jan Niehues · 2026-08-31 04:00

OmniFusion：通过模块化融合实现同步多语言多模态翻译

arXiv:2512.00234v3 Announce Type: replace Abstract: There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation…

本文如何被排名

报道来源 [1]

OmniFusion：通过模块化融合实现同步多语言多模态翻译

相关实体

相关话题