From the 1 of 20 linked papers with an AI index.
20 papers
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
Yushi Huang, Xiangxin Zhou, Jun Zhang +2
The paper introduces MeanFlowNFT, a method that applies reinforcement‑learning based reward optimization to MeanFlow generators by learning an instantaneous‑velocity predictor whil…
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
Xingtong Ge, Yi Zhang, Yushi Huang +6
Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency d…
Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
Chengtao Lv, Yumeng Shi, Yushi Huang +3
Advanced autoregressive (AR) video generation models have improved visual fidelity and interactivity, but the quadratic complexity of attention remains a primary bottleneck for eff…
Exploring the Design Space of Reward Backpropagation for Flow Matching
Ruoyu Wang, Boye Niu, Xiangxin Zhou +3
Aligning text-to-image flow matching models with human preferences via direct reward backpropagation is sample-efficient but hampered by two well-known pathologies: activations can…
Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
Yushi Huang, Xiangxin Zhou, Ruoyu Wang +3
Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-…
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
Zhuguanyu Wu, Ruihao Gong, Yang Yong +5
Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two co…