A theoretical framework to investigate perturbation propagation is developed, combining dynamical analysis of the sampling process with an information-theoretic characterization of output responses, and a response identity is derived that connects the propagation and accumulation of local perturbations with the informa...
Wei Guo, Yao-Wen Zhang, Xingtong Ge et al.· 0 citations
Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context and can propagate through subsequent rollouts, leading to detail degradation, structural drift, and unstable motion. Existing distribution matching distillation (DMD) prim...
Fang-Yu Lin, Xingtong Ge, Lu Zhu et al.· arXiv.org· 0 citations
Omni-LiveAvatar is presented, the first framework for minute-level, real-time streaming joint audio-video avatar generation and proposes a progressive autoregressive distillation pipeline that transfers a large bidirectional joint audio-video diffusion model into a few-step autoregressive generator without auxiliary st...
Lu Zhu, Xing-Tong Ge, Fang-Yu Lin et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.