PulseAugur
中
实时 10:18:11
English(EN) Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model

新波斯语检索模型Yalda-Embedding发布,采用开放开发模式

研究人员开发了Yalda-Embedding,一个拥有5.958亿参数的新波斯语检索模型,该模型改编自Qwen3-Embedding-0.6B。该模型在FaMTEB的八项波斯语检索任务上表现强劲,在评估的0.6B模型中取得了最高的宏平均分,并且优于其基础模型和F2LLM-v2-0.6B。开发过程包括对比微调和关系知识蒸馏,最终模型在不增加推理时大小的情况下,性能接近更大的Qwen3-Embedding-4B模型。该项目强调开放开发,发布模型权重、代码和数据集,以促进进一步的研究和再利用。 AI

影响 增强了波斯语人工智能应用的检索能力,并为进一步研究提供了开源资源。

排序理由 详细介绍用于检索任务的新语言模型的学术论文。[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 →

新波斯语检索模型Yalda-Embedding发布,采用开放开发模式

本文如何被排名

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍用于检索任务的新语言模型的学术论文。[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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli ·

    Yalda-Embedding:一个有竞争力的波斯语检索模型开放开发

    arXiv:2610.32933v1 Announce Type: cross Abstract: Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Em…