PulseAugur
实时 23:03:29
English(EN) RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain

新的RABBiT模型以高精度预测大脑对语音的反应

研究人员开发了RABBiT,这是一种新颖的音频到fMRI编码器,旨在以高精度预测零样本和少样本场景下大脑对语音的反应。该模型通过结合学习到的特定区域注意力并将大脑反应分解为共享和受试者特定成分,显著优于现有的最先进方法和群体平均水平。RABBiT的参数高效调优允许在最少的受试者特定数据的情况下实现显著的性能提升,从而能够对人类大脑中的语言进行更具可扩展性的分析。 AI

影响 通过提高预测精度和减少数据需求,能够对人类大脑中的语言进行更具可扩展性的群体水平分析。

排序理由 该集群包含一篇arXiv预印本,详细介绍了一个新的研究模型和方法。

在 arXiv cs.CL 阅读 →

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

新的RABBiT模型以高精度预测大脑对语音的反应

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Omer Moussa, Mariya Toneva ·

    RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain

    arXiv:2607.05171v1 Announce Type: new Abstract: Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generalize across both. This calls for a foundation model of …

  2. arXiv cs.CL TIER_1 English(EN) · Mariya Toneva ·

    RABBiT:通过大脑调优实现快速自适应BOLD基础模型,用于准确的零样本和少样本预测大脑中的语音引发反应

    Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generalize across both. This calls for a foundation model of language-evoked brain activity that can capture …