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...
Continuous-latent audio autoencoders form the backbone of latent music generators, yet decoders at high compression rates commonly exhibit three failure modes: high-frequency loss, phase incoherence, and stereo-image collapse. These share a structural root: waveform autoencoders lack an explicit frequency axis, leaving...
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
This work introduces TD-V2A, which leverages temporal differences (TD) as the key representation that distinguishes V2A from I2A, enriching visual conditioning with minimal architectural modification and significantly improves end-to-end V2A generation quality, even outperforming dedicated V2A representations such as c...
Zehua Chen, Junyou Wang, Yuxuan Jiang 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.