Although diffusion-based methods have substantially improved the controllability of multimodal face synthesis, their semantic alignment remains suboptimal because most existing approaches rely on implicit latent-space objectives to model the relationship between denoising variables and multimodal conditions. Such impli...
Yu-She Cao, Xue-Chao Zou, Xing Xi et al.· 0 citations
Multimodal Large Language Models have demonstrated impressive video understanding, yet their ability to reason over long-form narratives is often masked by visual-centric evaluations and inefficient context processing. Existing benchmarks over-rely on visual heuristics while marginalizing auditory cues, effectively red...
Zhao-Yang Wei, Zipeng Wang, Yu-She Cao et al.· 0 citations
LaP-Forensics is presented, a multimodal framework that augments RGB semantics with reconstruction-based forensic evidence that supports the utility of the residual stream under the evaluated settings, while free-form textual faithfulness and reliability under post-processing remain open limitations.
Can Wang, Yuhao Wang, Yu-She Cao et al.· arXiv.org· 1 citation
UniVVT is presented, a unified end-to-end framework that reframes VVT as semantically conditioned video generation, eliminating mask, pose, and warping modules at inference and validating implicit semantic guidance as a simple and effective alternative to fragile geometric preprocessing for end-to-end virtual try-on.
Yu-She Cao, Shikun Feng, Fei Shen et al.· 0 citations
LiveVVT is introduced, a rolling streaming diffusion framework that preserves bounded bidirectional modeling within causal recurrent generation, and a progressive distillation framework integrating bidirectional VVT learning, teacher-trajectory regression for causal few-step adaptation, and Collaborative Matching Disti...
Yu-She Cao, Shikun Feng, Ru-Xiang Duan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
