ICTNLP

Results 22 repositories owned by ICTNLP

LLaVA-Mini

546
Stars
28
Forks
546
Watchers

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

ComSpeech

25
Stars
6
Forks
25
Watchers

Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".