相关论文: A Systematic Evaluation of Sample-Level Tokenizati…

A major goal in neuroscience is to discover neural data representations that generalize. This goal is challenged by variability along recording sessions (e.g. environment), subjects (e.g. varying neural structures), and sensors (e.g. sensor…

Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-Tokenized Transformers, a novel framework that decouples…

Neuroimaging techniques have shown to be useful when studying the brain's activity. This paper uses Magnetoencephalography (MEG) data, provided by the Human Connectome Project (HCP), in combination with various deep artificial neural…

We present a foundation model for brain MRI that can work with different combinations of imaging sequences. The model uses one encoder with learnable modality embeddings, conditional layer normalization, and a masked autoencoding objective…

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in…

Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs). These tokenizers serve as the critical interface…

Decoding language from neural signals holds considerable theoretical and practical importance. Previous research has indicated the feasibility of decoding text or speech from invasive neural signals. However, when using non-invasive neural…

The vocabulary used by language models (LM) - defined by the tokenizer - plays a key role in text generation quality. However, its impact remains under-explored in radiology. In this work, we address this gap by systematically comparing…

Semiparametric language models (LMs) have shown promise in continuously learning from new text data by combining a parameterized neural LM with a growable non-parametric memory for memorizing new content. However, conventional…

Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, yielding representations that are rich but challenging for…

This paper presents an in-depth investigation on integrating neural language models in translation systems. Scaling neural language models is a difficult task, but crucial for real-world applications. This paper evaluates the impact on…

We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on…

This paper presents a novel approach towards creating a foundational model for aligning neural data and visual stimuli across multimodal representationsof brain activity by leveraging contrastive learning. We used electroencephalography…

Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…

The recent success of Large Language Models (LLMs) has been predominantly driven by curating the training dataset composition, scaling of model architectures and dataset sizes and advancements in pretraining objectives, leaving tokenizer…

Deep neural networks (DNNs) used for brain-computer-interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts.…

While there has been a large body of research attempting to circumvent tokenization for language modeling (Clark et al., 2022; Xue et al., 2022), the current consensus is that it is a necessary initial step for designing state-of-the-art…

This study investigates robust speech-related decoding from non-invasive MEG signals using the LibriBrain phoneme-classification benchmark from the 2025 PNPL competition. We compare residual convolutional neural networks (CNNs), an…

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…