Video token compression must control both temporal coverage and task relevance, but sequential stages can conflict: a content-driven allocation stage may be overwritten by a global ranking that removes entire temporal positions. We identify this as an allocation conflict and propose TeQCo, a training-free framework tha...
Yu-Qi Li, Xiang-Long Wang, Neilier Rodrigues et al.· 0 citations
Knowledge distillation enables efficient spatiotemporal prediction by transferring knowledge from an accurate teacher to a compact student. However, matching outputs or features independently for each sample leaves cross-sample predictive structure underused. Exploiting this structure requires representations and histo...
Yu-Qi Li, Xiao-Qin Feng, Fan Xu et al.· 0 citations
Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragi...
Wei-Lun Feng, Chuan-Guang Yang, Haotong Qin et al.· IEEE Transactions on Pattern...· 4 citations
Inspired by the Information Bottleneck principle, Prompted Information Bottlenecks (PIB) is introduced, a framework that regularizes layer-wise compression-sufficiency trade-offs and promotes a more coherent cross-layer information path.
Yuqi Li, Xi Xiao, Yun-Bei Zhang et al.· arXiv.org· 10 citations
A unified taxonomy that categorized existing methods into three primary paradigms: Interactive Generation, Interactive Editing, and Embodied Interaction is proposed that categorized existing methods into three primary paradigms and discussed their advantages and limitations.
Yu-Qi Li, Si-Wei Meng, Chuan-Guang Yang et al.· Proceedings of the Thirty-Fi...· 40 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
