FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Read the original on Hugging Face Trending Papers →FlashVSR+ is a new video super‑resolution model that tackles two main issues: the high cost of high‑resolution inference and the difficulty of aligning distilled models with human preferences. It introduces a hybrid attention architecture that combines strong local processing with sparse global interactions, achieving up to twice the speed of DiT and 45 % lower peak memory, which allows untiled 4K VSR on a single 24 GB RTX 4090. For training, the authors propose Reward‑Yield Distribution Matching Distillation (Ry‑DMD), a method that uses reward‑weighted teacher rollouts to incorporate black‑box rewards into distribution matching without backpropagating through the reward model, and demonstrate that Ry‑DMD generalizes beyond VSR to text‑to‑image generation.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.