Neighbor Forcing is proposed, a diffusion-step-consistent AR formulation that propagates temporally adjacent frames as latent neighbors under the same noise condition that provides a distribution-aligned and stable learning signal throughout the AR chain, and a structured ConvKV Memory mechanism that compresses the key...
Ding-Cheng Zhen, Xu Zheng, Rui-Xin Zhang et al.· Proceedings of the 34th ACM...· 0 citations
Autoregressive (AR) diffusion models offer a promising framework for sequential generation such as video synthesis by combining diffusion modeling with causal inference. Although they support streaming generation, existing AR diffusion methods struggle to scale efficiently. In this paper, we identify two key challenges...
Ding-Cheng Zhen, Xu Zheng, Rui-Xin Zhang et al.· Proceedings of the 34th ACM...· 0 citations
This approach substantially reduces the computation of long-context modeling, while enhancing the performance of the baseline model, achieving a speedup of 1.8$\times to 2.5$\times compared to the baseline VLLM.
Zihan Song, Shuo Ye, Bo Zhao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.