1
A More Word-like Image Tokenization for MLLMs
让图像分词更接近文本语义，提出新方法优化多模态大语言模型的融合效果。
arXiv:2605.17954v1 Announce Type: cross Abstract: Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a …
2
Tokenizing Single-Channel EEG with Time-Frequency Motif Learning
提出TFM-Tokenizer，从单通道脑电信号学习时频模式并编码为离散token，为EEG基础模型提供新思路。
arXiv:2502.16060v5 Announce Type: replace-cross Abstract: Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization r…