Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs (github.com/sony)
1 point by countWSS 9 months ago | hide | past | favorite | 1 comment


AKI, a novel MLLM that unlocks causal attention into modality-mutual attention (MMA) to enable image tokens to attend to text tokens.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: