In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by the integration of machine learning and artificial intelligence. This survey aims to encapsulate the latest developments, focusing on emerging methods and technologies that are poised to transform our comprehension and interpretation of brain activity. The structure of this paper is organized according to the categorization within the machine learning community, with representation learning as the foundational concept that encompasses both discriminative and generative approaches. We delve into self-supervised learning methods that enable the robust representation of brain signals, which are fundamental for a variety of downstream applications. Within the realm of discriminative methods, we explore advanced techniques such as graph neural networks (GNN), foundation models, and approaches based on large language models (LLMs). On the generative front, we examine technologies that leverage EEG data to produce images or text, offering novel perspectives on brain activity visualization and interpretation. This survey provides an extensive overview of these cutting-edge techniques, their current applications, and the profound implications they hold for future research and clinical practice. The relevant literature and open-source materials have been compiled and are consistently updated at https://github.com/wpf535236337/LLMs4TS.

Given the significant potential of large language models (LLMs) in sequence modeling, emerging studies have begun applying them to time-series forecasting. Despite notable progress, existing methods still face two critical challenges: (1) their reliance on large amounts of paired text data, limiting the model applicability, and (2) a substantial modality gap between text and time series, leading to insufficient alignment and suboptimal performance. This paper introduces Hierarchical Text-Free Alignment (TS-HTFA) a novel method that leverages hierarchical alignment to fully exploit the representation capacity of LLMs for time-series analysis while eliminating the dependence on text data. Specifically, paired text data are replaced with adaptive virtual text based on QR decomposition word embeddings and learnable prompts. Furthermore, comprehensive cross-modal alignment is established at three levels: input, feature, and output, contributing to enhanced semantic symmetry between modalities. Extensive experiments on multiple time-series benchmarks demonstrate that TS-HTFA achieves state-of-the-art performance, significantly improving prediction accuracy and generalization.

Huanran Zheng, Xiaoling Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.