EFlow：通过高效解流实现从零开始的快速少步视频生成训练
EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
AI总结：
本文提出EFlow框架，通过高效解流目标和改进的训练方法，减少采样步骤和计算成本，实现更高的训练吞吐量和更低的推理延迟。
摘要：
本文提出EFlow框架，通过高效解流目标和改进的训练方法，减少采样步骤和计算成本，实现更高的训练吞吐量和更低的推理延迟。
英文摘要：
Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step training framework, that tackles these bottlenecks simultaneously. To reduce sampling steps, we build on a solution-flow objective that learns a function mapping a noised state at time t to time s. Making this formulation computationally feasible and high-quality at video scale, however, demands two complementary innovations. First, we propose Gated Local-Global Attention, a token-droppable hybrid block which is efficient, expressive, and remains highly stable under aggressive random token-dropping, substantially reducing per-step compute. Second, we develop an efficient few-step training recipe. We propose Path-Drop Guided training to replace the expensive guidance target with a computationally cheap, weak path. Furthermore, we augment this with a Mean-Velocity Additivity regularizer to ensure high fidelity at extremely low step counts. Together, our EFlow enables a practical from-scratch training pipeline, achieving up to 2.5x higher training throughput over standard solution-flow, and 45.3x lower inference latency than standard iterative models with competitive performance on Kinetics and large-scale text-to-video datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
