Tag
FlashVSR+ 提出基于混合注意力的高效视频超分辨率架构与 Reward-Yield 分布匹配蒸馏（Ry-DMD），实现 2 倍 DiT 加速、45% 峰值显存降低，可在单张 24GB RTX 4090 上完成 4K 视频超分，并支持黑盒奖励对齐的单步生成。
This paper introduces ARIA, a framework that adaptively allocates training effort across regions of the conditioning space for distilling conditional diffusion models, improving performance on unseen and underrepresented conditions.
This paper introduces Causal-rCM, a unified teacher-forcing and self-forcing framework for autoregressive diffusion distillation in streaming video generation and interactive world models, achieving state-of-the-art performance with fast convergence.
This paper introduces Z-Image Turbo++, a two-step image generation model distilled from an eight-step teacher using distribution-aligned adversarial learning, step-decoupled parameterization, and end-to-end training with iterative regularization to narrow the quality gap with multi-step generation.
RTDMD is a two-stage framework combining distribution matching distillation with reward-guided reinforcement learning to improve few-step image generation alignment with human preferences. It achieves state-of-the-art results on multiple models with only 4 inference steps.
Causal Forcing++ presents a novel causal consistency distillation method for frame-wise autoregressive video generation, achieving state-of-the-art quality with reduced latency and training cost.