| title | FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching |
|---|---|
| authors | Ruchang Yao, Shi Guo, Junhao Zhuang, Mingde Yao, Xin Cai, Jiahao Zhan, Bin Fu, Xinyuan Chen, Yu Qiao, Tianfan Xue |
| date | 2026-10-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.17552 |
| affiliation | MMLab-CUHK |
| upvotes | 30 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled models are difficult to align with human preferences. These challenges call for improvements in both model architecture and training strategy. We present FlashVSR+ to address both limitations. On the architecture side, we introduce hybrid attention based on the strong locality observed in pretrained VSR models, while retaining sparse global interaction for long-range consistency. It achieves up to 2times DiT speedup and 45\% lower peak memory, enabling spatially untiled 4K VSR on a single 24GB RTX 4090. On the training side, we propose Reward-Yield Distribution Matching Distillation (Ry-DMD) for preference-aligned one-step generation. Ry-DMD uses reward-weighted teacher rollouts to incorporate black-box rewards into distribution matching, without backpropagating through the reward model. We further show that Ry-DMD generalizes beyond VSR to T2I generation. Together, FlashVSR+ delivers stronger restoration quality and substantially improves high-resolution efficiency, with consistent gains in user preference. We release our code, models, and training data at https://www.flashvsr.tech{FlashBlue{www.flashvsr.tech}}. |
cite
@misc{yao2026flashvsr,
title={FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching},
author={Ruchang Yao and Shi Guo and Junhao Zhuang and Mingde Yao and Xin Cai and Jiahao Zhan and Bin Fu and Xinyuan Chen and Yu Qiao and Tianfan Xue},
year={2026},
eprint={2610.17552},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.17552}
}