Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

2026-02-02

AI Summary

This work addresses the performance degradation and lack of theoretical guarantees in existing approaches when distilling bidirectional video diffusion models into autoregressive ones, primarily due to architectural mismatches. The authors propose Causal Forcing, a novel method that leverages an autoregressive teacher model to guide the initialization of the ordinary differential equation (ODE) solver, effectively bridging the architectural gap between bidirectional and causal attention mechanisms. This approach provides the first theoretical resolution to the frame-level non-injectivity issue inherent in autoregressive distillation, ensuring invertibility of the flow map and circumventing performance loss caused by conditional expectation solutions. Built upon an ODE-based distillation framework and integrating autoregressive diffusion with causal attention, the method achieves state-of-the-art results, surpassing prior art by 19.3%, 8.7%, and 16.7% on Dynamic Degree, VisionReward, and Instruction Following metrics, respectively, enabling high-quality, real-time interactive video generation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Causal Learning
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by causal attention. However, existing approaches do not bridge this gap theoretically. They initialize the AR student via ODE distillation, which requires frame-level injectivity, where each noisy frame must map to a unique clean frame under the PF-ODE of an AR teacher. Distilling an AR student from a bidirectional teacher violates this condition, preventing recovery of the teacher's flow map and instead inducing a conditional-expectation solution, which degrades performance. To address this issue, we propose Causal Forcing that uses an AR teacher for ODE initialization, thereby bridging the architectural gap. Empirical results show that our method outperforms all baselines across all metrics, surpassing the SOTA Self Forcing by 19.3\% in Dynamic Degree, 8.7\% in VisionReward, and 16.7\% in Instruction Following. Project page and the code: \href{https://thu-ml.github.io/CausalForcing.github.io/}{https://thu-ml.github.io/CausalForcing.github.io/}

Problem

• autoregressive diffusion
• video generation
• architectural gap
• causal attention
• distillation

Innovation

• Causal Forcing
• Autoregressive Diffusion
• ODE Distillation
• Real-Time Video Generation
• Architectural Gap