Xinyuan Xie's picture

2 3 1

Xinyuan Xie

SatsukiVie

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

upvoted a paper 3 months ago

ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

new activity 3 months ago

SatsukiVie/FusionAudio:About the number of sample ids

View all activity

Organizations

Papers 1

arxiv:2506.01111

models 1

SatsukiVie/FusionAudio

Updated May 16 • 3

datasets 1

SatsukiVie/FusionAudio

Viewer • Updated Jun 8 • 6.07M • 139 • 8