中文
相关论文

相关论文: Riding Brainwaves in LLM Space: Understanding Acti…

200 篇论文

EEG foundation models (EEG-FMs) have been evaluated predominantly on clean, in-distribution accuracy, leaving their robustness, interpretability and representational quality largely unexamined. This study addresses these gaps by…

机器学习 · 计算机科学 2026-05-19 Urban Širca , Maryam Alimardani , Stefanos Zafeiriou , Konstantinos Barmpas

How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions across languages, but…

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the…

Conventional biometrics have been employed in high security user authentication systems for over 20 years now. However, some of these modalities face low security issues in common practice. Brain wave based user authentication has emerged…

密码学与安全 · 计算机科学 2022-07-15 Christos Stergiadis , Vasiliki-Despoina Kostaridou , Simeon Veloudis , Dimitrios Kazis , Manousos Klados

Electroencephalography (EEG) recordings of brain activity taken while participants read or listen to language are widely used within the cognitive neuroscience and psycholinguistics communities as a tool to study language comprehension.…

计算与语言 · 计算机科学 2019-11-05 Dan Schwartz , Tom Mitchell

Language and vision-language models have shown impressive performance across a wide range of tasks, but their internal mechanisms remain only partly understood. In this work, we study how individual attention heads in text-generative models…

计算机视觉与模式识别 · 计算机科学 2026-01-15 Lorenzo Basile , Valentino Maiorca , Diego Doimo , Francesco Locatello , Alberto Cazzaniga

Linguistic information is encoded at varying timescales (subwords, phrases, etc.) and communicative levels, such as syntax and semantics. Contextualized embeddings have analogously been found to capture these phenomena at distinctive layers…

计算与语言 · 计算机科学 2022-10-24 Max Müller-Eberstein , Rob van der Goot , Barbara Plank

Predictive coding theory suggests that the brain continuously anticipates upcoming words to optimize language processing, but the neural mechanisms remain unclear, particularly in naturalistic speech. Here, we simultaneously recorded EEG…

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions…

计算与语言 · 计算机科学 2026-05-14 Hannah Rose Kirk , Liu Leqi , Fanzhi Zeng , Henry Davidson , Bertie Vidgen , Christopher Summerfield , Scott A. Hale

There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…

音频与语音处理 · 电气工程与系统科学 2023-09-06 Minh Tran , Yufeng Yin , Mohammad Soleymani

Large language models (LLMs) are increasingly explored as substitutes for human participants in cognitive tasks, but their ability to simulate human behavioral variability remains unclear. This study examines whether LLMs can approximate…

计算与语言 · 计算机科学 2026-02-27 Mengyang Qiu , Zoe Brisebois , Siena Sun

Physically Assistive Robots (PARs) require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause severe physical and cognitive fatigue for…

机器人学 · 计算机科学 2026-04-03 Keshav Shankar , Dan Ding , Wei Gao

Decoding EEG signals is crucial for unraveling human brain and advancing brain-computer interfaces. Traditional machine learning algorithms have been hindered by the high noise levels and inherent inter-person variations in EEG signals.…

信号处理 · 电气工程与系统科学 2024-03-26 Pengfei Sun , Jorg De Winne , Paul Devos , Dick Botteldooren

This paper introduces the Luca-Noise Reflex Protocol (LN-RP), a computational framework for analyzing noise-driven persona emergence in large language models. By injecting stochastic noise seeds into the initial generation state, we observe…

计算与语言 · 计算机科学 2026-01-01 Toshiyuki Shigemura

The ongoing revolution in language modeling has led to various novel applications, some of which rely on the emerging social abilities of large language models (LLMs). Already, many turn to the new cyber friends for advice during the…

计算机与社会 · 计算机科学 2025-08-05 Ivan Zakazov , Mikolaj Boronski , Lorenzo Drudi , Robert West

EEG-based person identification enables applications in security, personalized brain-computer interfaces (BCIs), and cognitive monitoring. However, existing techniques often rely on deep learning architectures at high computational cost,…

神经与进化计算 · 计算机科学 2025-10-22 Zheyuan Lin , Siqi Cai , Haizhou Li

Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity, yet it remains unclear what drives these gains and which representational properties are responsible. Although larger models…

A language is made up of an infinite/finite number of sentences, which in turn is composed of a number of words. The Electrocardiogram (ECG) is the most popular noninvasive medical tool for studying heart function and diagnosing various…

信号处理 · 电气工程与系统科学 2024-07-17 Prapti Ganguly , Wazib Ansar , Amlan Chakrabarti

Recent advancements in Large Language Models have inspired the development of foundation models across various domains. In this study, we evaluate the efficacy of Large EEG Models (LEMs) by fine-tuning LaBraM, a state-of-the-art foundation…

机器学习 · 计算机科学 2025-05-30 Siwen Wang , Shitou Zhang , Wan-Lin Chen , Dung Truong , Tzyy-Ping Jung

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention…

计算与语言 · 计算机科学 2024-04-16 Xintong Wang , Xiaoyu Li , Xingshan Li , Chris Biemann