一瞥强制：让双向扩散模型实现一瞥式自回归
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
AI总结：
本文提出Glance Forcing轻量蒸馏框架，将双向扩散模型的去噪轨迹解耦为快慢专家，仅用1条PF-ODE轨迹就提升了视频生成质量并大幅降低了成本。
摘要：
自回归生成是实时因果视频合成的基础，也是视频世界模型的核心支撑。当前主流方法将双向扩散模型蒸馏为因果少步学生模型，但现有转换流程成本极高，需要离线概率流常微分方程（PF-ODE）轨迹，耗时达数万个GPU小时，存储量达数TB。本文证明可大幅提升该过程效率：将轨迹监督减少到单个样本（最严格设置），但发现这会导致严重的质量崩溃，原因是教师模型的轨迹几何存在差异——控制语义布局和运动的高噪声区域，与控制精细纹理的低噪声区域具有完全不同的曲率和优化行为，单一整体学生模型无法同时适配两者，导致严重的表示干扰。基于此，本文提出Glance Forcing，一种轻量蒸馏框架，将去噪轨迹解耦为互补的慢、快两个专家，每个专家由量身定制的、特定阶段的目标引导，同时保持预训练教师模型完全冻结。这种解耦进一步揭示了少步蒸馏的通用机制：PF-ODE蒸馏主要拉直少步轨迹几何，后续分布匹配阶段则独立控制分布质量。仅使用1条PF-ODE轨迹，Glance Forcing就已超过完全训练的最先进基线，将VBench总分从84.04提升至84.22，同时将轨迹收集成本从数千个GPU小时削减至约1个A100-GPU小时，在动态程度、VisionReward和指令遵循方面获得显著更大的提升，且人类评估者对其的偏好始终强于强基线。
英文摘要：
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bidirectional diffusion model into a causal few-step student, but existing pipelines make this conversion prohibitively expensive, requiring offline Probability Flow ODE} (PF-ODE) trajectories that cost tens of thousands of GPU-hours and terabytes of storage. We show it can be made dramatically more efficient. Pushing this efficiency to its extreme, we reduce trajectory supervision to a single sample, the strictest setting possible, and find that it causes severe quality collapse. We trace this to the teacher's trajectory geometry: the high-noise regime, governing semantic layout and motion, and the low-noise regime, governing fine texture exhibit fundamentally different curvature and optimization behavior, so a single monolithic student cannot jointly fit both, causing severe representation interference. Motivated by this, we propose Glance Forcing, a lightweight distillation framework that decouples the denoising trajectory into two complementary slow and fast experts, each guided by a tailored, stage-specific objective, while keeping the pretrained teacher entirely frozen. This decoupling further reveals a general mechanism underlying few-step distillation: PF-ODE distillation mainly straightens the few-step trajectory geometry, while the subsequent distribution-matching stage independently governs distributional quality. Using only one PF-ODE trajectory, Glance Forcing already surpasses the fully-trained state-of-the-art baseline, raising the VBench Total score from 84.04 to 84.22 while cutting trajectory-collection cost from thousands of GPU-hours to about one A100-GPU-hour, with markedly larger gains in dynamic degree, VisionReward, and instruction-following, and consistent preference from human raters over strong baselines.
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。
