RepForcing: Representation-Space Initialization for Autoregressive Video Distillation

Siming Fu; Zheming Fu; Lianrui Mu; Haoyang Huang; Chaojie Gu; Ruizhe He

cs.CVOct 14, 2026

RepForcing: Representation-Space Initialization for Autoregressive Video Distillation

Authors: Siming Fu, Zheming Fu, Lianrui Mu, Haoyang Huang, Chaojie Gu, Ruizhe He

Organizations: Joy Future Academy · Zhejiang University

Abstract

Distilling pretrained video diffusion models into few-step autoregressive (AR) generators typically combines student initialization with distribution matching distillation (DMD). An intermediate AR teacher can provide causally compatible targets for ODE initialization. However, causally compatible targets alone do not ensure high-quality generation under a short sampling schedule. We analyze the posterior-mean predictions favored by direct latent regression and empirically find that causal ODE initialization alleviates blur but still leaves fine detail unresolved. To address this limitation, we propose Representation Forcing, which learns few-step causal initialization through representation-space supervision rather than intermediate-teacher trajectory regression. The student is trained with teacher forcing by comparing clean predictions and training targets through normalized features of a frozen video diffusion transformer. This phase reuses the synthetic videos generated by a bidirectional model for AR teacher training and replaces both teacher training and causal ODE distillation, without generating additional causal ODE trajectories. The subsequent asymmetric DMD procedure remains unchanged. Empirical results show that, at four sampling steps, RepForcing better preserves generation quality than intermediate-teacher-based initialization before DMD. After DMD, our four-step chunk-wise model improves VBench Total from 84.04 to 84.66 (+0.62 points) and VisionReward from 6.326 to 10.074 (+59.25%) over the reported causal-ODE-based baseline.

Figures & tables

Figure 1: High-Quality Videos Generated by RepForcing. The examples span human activities, animal behavior, and stylized scenes, showing details such as clothing folds, fur, and vegetation. Across the displayed frames, subjects change pose and position while retaining their appearance and surrounding scene structure.

Figure 2: RepForcing Initialization Better Preserves Generation Quality as Sampling Steps Decrease. Rows compare three initialization strategies: teacher-forced AR training followed by ODE distillation, teacher-forced AR training followed by consistency distillation, and direct representation-space initialization, from top to bottom. All results are shown before subsequent refinement. Columns show 4, 8, and 12 sampling steps from left to right, with two frames per setting for the same prompt. With more denoising steps, ODE initialization approaches the visual quality of RepForcing. At four steps, however, the intermediate-teacher initializations exhibit blur or structural artifacts, while RepForcing maintains coherent subject and scene structure.

Figure 3: Representation Forcing Initialization Pipeline. Training videos are encoded into clean latent blocks by a VAE encoder. The trainable causal DiT reconstructs clean blocks from noisy inputs, conditioned on preceding clean blocks under teacher forcing. The predicted and target video latents are passed separately through the same truncated, frozen Wan2.1-14B to obtain features $\hat{\mathbf{f}}$ and $\mathbf{f}$ . A token-wise cosine loss compares these features, with stop-gradient ( $\operatorname{sg}$ ) on the target branch. Gradients propagate through the frozen extractor to update the causal DiT. This initialization replaces intermediate AR teacher training and causal ODE distillation.

Figure 4: Qualitative comparison of chunk-wise distilled autoregressive models. For each of four prompts, three sampled frames are shown for CausVid, Self Forcing, Causal Forcing, Causal-rCM, and RepForcing. The RepForcing examples retain visible fur strands and facial detail in the character scene, together with clothing folds, hanging blossoms, and rock textures in the human scenes. Changes in body and hand pose are visible across the sampled frames.

Model	Total $\uparrow$	Quality $\uparrow$	Semantic $\uparrow$	Dynamic. $\uparrow$	Vision. $\uparrow$	Instruct. $\uparrow$
Bidirectional video models
LTX-1.9B ( HaCohen et al., 2024 )	79.83	81.88	71.62	46	$-6.218$	$-38$
Wan2.1-1.3B ( Wan et al., 2025 )	83.37	84.30	79.65	61	5.275	42
Autoregressive video models
NOVA ( Deng et al., 2025 )	80.31	80.66	78.92	46	$-7.381$	$-16$
Pyramid Flow ( Jin et al., 2025 )	80.75	83.41	70.11	16	4.055	$-2$

Table 1: Comparison with existing methods. Dynamic., Vision., and Instruct. denote Dynamic Degree, VisionReward, and Instruction Following. Bold marks column-wise best results within each distilled AR group, including ties; empty cells are unreported. Baseline scores follow Zhu et al. (2026) ; frame-wise four-step Causal Forcing++ scores come from its own report ( Zhao et al., 2026 ) , and Causal-rCM scores are obtained from evaluations of pretrained weights ( Zheng et al., 2026 ) .

Ablation	Setting	Total $\uparrow$	Quality $\uparrow$	Semantic $\uparrow$	Dynamic. $\uparrow$	Vision. $\uparrow$	Instruct. $\uparrow$
Repr. Model	DINOv2	82.82	83.73	79.15	75	5.947	53
	InternVid	83.08	84.33	78.05	64	7.653	62
	Wan2.1-14B	84.66	85.55	81.10	69	10.074	78
Relative Depth	$1/8$	84.49	85.45	80.64	61	9.217	69
	$\bm{1/5}$	84.66	85.55	81.10	69	10.074	78
	$1/2$	84.58	85.51	80.86	65	9.893	77

Table 2: Ablation Study on Representation Models and Extraction Depth. All variants are evaluated with chunk-wise four-step generation after matched DMD refinement. Repr. Model compares feature extractors, while Relative Depth varies the extraction position within Wan2.1-14B. The default representation model is shown in bold. Dynamic., Vision., and Instruct. denote Dynamic Degree, VisionReward, and Instruction Following.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 5: Qualitative comparison of frame-wise autoregressive models. Each quadrant shows three sampled frames for the same prompt across Causal Forcing, Causal Forcing++, and RepForcing (top to bottom). The examples depict a girl peeling an orange (top left), a mountaineer overlooking a frozen fjord (top right), a mother bird feeding her chicks (bottom left), and a woman holding flowers above a lake (bottom right).

Diffusion Model Distillation

Diffusion model distillation transfers a large model’s generative behavior to faster or smaller models that need fewer sampling steps.

See all 183 papers

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
May 14, 2026Min Zhao, Hongzhou Zhu, Kaiwen Zheng +6Autoregressive Diffusion Real-Time Interactive Video Generation
Tsinghua University · ShengShu · Renmin University of China
From Scores to Samples: Elastic Forcing for Autoregressive Video Generation
Sep 28, 2026Chi Zhang, Yueyi Liu, Shi Haoyang +5Autoregressive Video Generation
College of AI, Tsinghua University · IAIR, Xi’an Jiaotong University · Xianghui Academy, Fudan University +1
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Sep 24, 2026Zichong Meng, Chongjian Ge, Chun-Hao P. Huang +2Diffusion Model Distillation Distribution Matching
Northeastern University · Adobe Research

May 14, 2026J/K move · Enter open · S save

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Min Zhao, Hongzhou Zhu, Kaiwen Zheng, Zihan Zhou+5

Tsinghua University · ShengShu · Renmin University of China

Autoregressive Diffusion Real-Time Interactive Video Generation Streaming Video Generation Few-Step Diffusion Sampling Autoregressive Video Generation Causal Video Generation

Open paper AskPDF arXiv

Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies are either target-misaligned, incapable of few-step generation, or too costly to scale. We propose Causal Forcing++, a principled and scalable pipeline that uses causal consistency distillation (causal CD) for few-step AR initialization. The core idea is that causal CD learns the same AR-conditional flow map as causal ODE distillation, but obtains supervision from a single online teacher ODE step between adjacent timesteps, avoiding the need to precompute and store full PF-ODE trajectories. This makes the initialization both more efficient and easier to optimize. The resulting pipeline, \ours, surpasses the SOTA 4-step chunk-wise Causal Forcing under the frame-wise 2-step setting by 0.1 in VBench Total, 0.3 in VBench Quality, and 0.335 in VisionReward, while reducing first-frame latency by 50% and Stage 2 training cost by

\sim$$4\times

. We further extend the pipeline to action-conditioned world model generation in the spirit of Genie3. Project Page: https://github.com/thu-ml/Causal-Forcing and https://github.com/shengshu-ai/minWM .

Abstract

Diffusion Model Distillation

Explore similar work

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

From Scores to Samples: Elastic Forcing for Autoregressive Video Generation

ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation