2 papers
cs.CV2026
Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain
Guangyuan Li, Tianming Du, Yan Jiang +2
CLIP-like vision-language models remain a cornerstone of multimodal systems, yet their scores stay near chance on directed spatial relations, such as whether one object is left of…
cs.LG2026
NeurDuo-EEG: A Long-Sequence EEG Foundation Model with Persistent State and Explicit Memory
Yifan Wang, Haiping Liu, Yang Cui +13
Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG foundation models nevertheless pro…