Author

Huafeng Shi

h-index 7 View on Semantic Scholar

We have 2 of 12 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation

Autoregressive video diffusion enables causal video streaming without a bidirectional pass over the full clip, but existing few-step systems usually retain only the opening and most recent frames in a fixed-size KV cache. Once an event leaves this window, later frames can no longer attend to it, a failure we term mid-h...

Jia-Ming Zhang, Xinyu Wang, Hua-Feng Shi et al. · 0 citations

Jul 2026

Vera: Identity-Faithful Human Subject-to-Video Generation

Vera is proposed, a unified human-centric S2V framework for single- and multi- person generation that improves human identity consistency, multi-person subject binding, and motion naturalness, while reducing identity confusion and excessive reference-image copying.

Yulong Xu, Xinyue Liu, Shujuan Li et al. · arXiv.org · 0 citations