Search papers, labs, and topics across Lattice.
This paper introduces the Brain Latent Predictive Model (BLPM), which reformulates EEG decoding tasks into a continuous semantic embedding prediction framework to enhance the integration of EEG data with natural language semantics. By employing a Continuous EEG Latent Predictive (CELP) encoder and a Multi-Query Semantic Decomposition (MQSD) module, the model effectively aligns continuous EEG representations with textual semantics, addressing the limitations of traditional masked autoencoding and autoregressive methods. Experimental results across various benchmarks show that BLPM achieves superior generalization performance, underscoring the efficacy of continuous latent semantic prediction in EEG-language modeling.
Transforming EEG decoding into a continuous semantic embedding task unlocks new levels of generalization in EEG-language models.
Recent advances in EEG foundation models have demonstrated the potential of large-scale pretraining to enable generalizable neural decoding across subjects, recording environments, and datasets. However, dominant pretraining paradigms face key challenges: masked autoencoding tends to prioritize low-level signal reconstruction over task-relevant semantics, while autoregressive modeling creates a mismatch between continuous neural dynamics and discrete token spaces. To address these challenges, new strategies are needed to effectively align continuous EEG representations with natural-language semantics and enable their integration with large language models. Accordingly, we propose Brain Latent Predictive Model (BLPM), an EEG-language foundation model that reformulates heterogeneous EEG decoding tasks as a continuous semantic embedding prediction problem. BLPM introduces a Continuous EEG Latent Predictive (CELP) encoder that learns transferable representations through latent target prediction. Building on these representations, a Multi-Query Semantic Decomposition (MQSD) module extracts task-relevant information and aligns continuous EEG representations with textual semantics within a shared latent space according to their semantic relationships. Experiments across multiple benchmarks demonstrate consistent generalization performance across diverse tasks, establishing continuous latent semantic prediction as an effective paradigm for EEG-language foundation models.
