Jul 2026
WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation
WaveZip is proposed, a joint signal-frequency-domain framework for efficient video inference that requires no task-specific training and can be seamlessly integrated into off-the-shelf LVLMs to boost inference efficiency.
Yuhui Zeng, Wang Chen, Jin-Fa Huang et al.
· arXiv.org · 1 citation