SekiyoKana

sekiyokana

2

AI & ML interests

None yet

Recent Activity

upvoted a paper 14 days ago

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

upvoted an article 3 months ago

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

View all activity

Organizations

None yet

upvoted a paper 14 days ago

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Paper • 2609.33419 • Published 16 days ago • 19

upvoted an article 3 months ago

Article

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

ResterChed

•

Jul 24

• 25