Multimodal Models

SAE-V: Interpreting Multimodal Models for Enhanced Alignment
SAE-V: Interpreting Multimodal Models for Enhanced Alignment
Hantao Lou , Changye Li , Jiaming Ji , Yaodong Yang
ICML 2025
AI Alignment, Multimodal Models
PDF
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Jiaming Ji , Jiayi Zhou , Hantao Lou , Boyuan Chen , Donghai Hong , Xuyao Wang , Wenqi Chen , ... show more (7 authors) , Dong Li , Weipeng Chen , Jun Song , Bo Zheng , Yaodong Yang
Arxiv 2025
AI Alignment, Multimodal Models
PDF Code Dataset