TY  - RPRT
TI  - SAIL: Sparse Autoencoders for Interpretable Alignment of Human Vision and Multimodal Large Language Models
AU  - Gao, T.
AU  - Zhang, L.
AU  - Wang, Y.
AU  - Zhou, H.
AU  - Xue, M.
AU  - Yang, G.
PY  - 2026
DO  - 10.64898/2026.09.30.755515
UR  - https://www.biorxiv.org/content/10.64898/2026.09.30.755515v1
ID  - 10.64898/2026.09.30.755515
ER  -