arxiv:2607.23265
Yuhui
Yuvye
ยท
AI & ML interests
Multimodal
Recent Activity
authored a paper 1 day ago
TimePLE: Rethinking Temporal Representation for Video Temporal Grounding authored a paper 1 day ago
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation authored a paper 1 day ago
CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning