English

DELTA: Language Diffusion-based EEG-to-Text Architecture

Computation and Language 2025-12-01 v1

Abstract

Electroencephalogram (EEG)-to-text remains challenging due to high-dimensional noise, subject variability, and error accumulation in autoregressive decoding. We introduce DELTA, which pairs a Residual Vector Quantization (RVQ) EEG tokenizer with a masked language diffusion model (LLaDA). RVQ discretizes continuous EEG into multi-layer tokens to reduce noise and individual differences, while LLaDA reconstructs sentences via non-sequential denoising. On ZuCo, DELTA improves semantic alignment by up to 5.37 points over autoregressive baselines, achieving BLEU-1 21.9 and ROUGE-1 F 17.2 under word-level conditions. These results enable reliable text generation from small EEG-text datasets and point toward scalable multimodal EEG-language models.

Cite

@article{arxiv.2511.21746,
  title  = {DELTA: Language Diffusion-based EEG-to-Text Architecture},
  author = {Mingyu Jeon and Hyobin Kim},
  journal= {arXiv preprint arXiv:2511.21746},
  year   = {2025}
}
R2 v1 2026-07-01T07:56:52.234Z