Tag
提出InterpTok,通过在训练样本之间的代码混合空间中训练解码器来改进图像tokenizer的插值与生成质量,在MAETok基础上将插值质量提升三倍以上,并将扩散transformer的生成FID从11.61降至8.48(无引导)。
This paper systematically evaluates masking strategies for EEG foundation models across MAE and JEPA frameworks, identifying optimal configurations and a novel failure mode, achieving comparable performance to REVE with reduced compute.