A Trailing Sliding Window that converts non-causal segment-level encoders into streaming modules without retraining and a Trailing Sliding Window that converts non-causal segment-level encoders into streaming modules without retraining is introduced.
Yu-Sheng Dai, Vladimir E. Iashin, Kang-Di Wang et al.· 0 citations
CineDub is a unified diffusion-based model that achieves precise multi-speaker dialogue dubbing directly from uncropped videos, without face cropping or speaker diarization, and introduces an Ambient-to-Linguistic Curriculum Learning (ALC) to mitigate sub-task degradation, and a decoupled textual branch control mechani...
Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet finite rollouts leave long-range drift unresolved. We observe that the noise level of the history key-value (K/V) representations trades visua...
Weiqiang Wang, Zhuo-Kun Chen, Yu-Sheng Dai et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.