因果-rCM：一種統一的教師強迫與自我強迫開放式配方，用於串流影片生成與互動世界模型中的自回歸擴散蒸餾

摘要

自回归视频扩散結合因果擴散變換器，已成為即時串流影片生成與動作條件式互動世界模型的主要典範。在本研究中，我們將先進的擴散蒸餾框架 rCM 擴展至自迴歸視頻擴散。rCM 的核心哲學在於擴散蒸餾中，前向發散與反向發散之間的互補性——分別由一致性模型（CM）與分佈匹配蒸餾（DMD）代表。此哲學自然延伸至自迴歸設定中，其中教師強制（TF）提供一種離線的前向發散因果訓練典範，而自我強制（SF）則對應於在策略的反向發散精煉。我們的貢獻如下：（1）透過大量實驗，我們證明教師強制一致性模型目前作為初始化策略時，是自我強制 DMD 的最佳互補方案；（2）我們首次實現基於教師強制的連續時間一致性模型（例如 sCM/MeanFlow）應用於自迴歸視頻擴散，藉助我們自訂遮罩的 FlashAttention-2 JVP 核心，實現比離散時間一致性模型（dCM）快 10 倍的收斂速度；（3）我們提出 Causal-rCM，一個領先、統一且可擴展的演算法-基礎設施開放配方，專用於擴散蒸餾與因果訓練；（4）我們在逐幀與逐區塊設定下，僅使用合成資料進行訓練，即達到串流影片生成的業界最佳表現。值得注意的是，我們蒸餾後的 2 步因果 Wan2.1-1.3B 模型，僅需 1 或 2 個取樣步驟即可達到 VBench-T2V 分數 84.63。我們進一步將 Causal-rCM 應用於 Cosmos 3——一個用於物理 AI 的先進全模態世界基礎模型，具備動作條件式生成能力，從而實現互動式世界模型。

English

Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work, we extend rCM, an advanced diffusion distillation framework, to autoregressive video diffusion. The core philosophy of rCM lies in the complementarity between forward and reverse divergences, represented by consistency models (CMs) and distribution matching distillation (DMD), respectively, in diffusion distillation. This philosophy naturally carries over to the autoregressive setting, where teacher-forcing (TF) provides an offline, forward-divergence causal training paradigm, while self-forcing (SF) corresponds to an on-policy, reverse-divergence refinement. Our contributions are: (1) through extensive experiments, we show that teacher-forcing CM is currently the best complement to self-forcing DMD as an initialization strategy (2) we present the first implementation of teacher-forcing-based continuous-time CMs (e.g., sCM/MeanFlow) for autoregressive video diffusion, enabled by our custom-mask FlashAttention-2 JVP kernel, achieving 10times faster convergence compared to discrete-time CMs (dCMs) (3) we introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training (4) we achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training. Notably, our distilled 2-step causal Wan2.1-1.3B model achieves a VBench-T2V score of 84.63 with only 1 or 2 sampling steps. We further apply Causal-rCM to Cosmos 3, an advanced omnimodal world foundation model for physical AI with action-conditioned generation capability, enabling an interactive world model.