Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

• URL: http://arxiv.org/abs/2609.09123v1
• Date: Tue, 08 Sep 2026 17:50:05 GMT
• Title: Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout
• Abstract summary: Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD)<n>The generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism.<n>We propose Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse.
• Score: 28.90854720290184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods distill pretrained bidirectional video diffusion models into causal AR students through Distribution Matching Distillation (DMD), but the generated videos often suffer from over-saturation and over-smoothing issues, resulting in limited visual quality and realism. The key contributing factor is the mode-seeking behavior of the reverse KL objective in DMD, which can cause the student distribution to collapse onto only a few modes of the teacher distribution. To address this, we propose Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse induced by reverse-KL mode seeking. The core idea is to inject cleaner signals into noisy rollout inputs via random masks along spatial and temporal axes during the self-rollout process of AR diffusion distillation. Such perturbations encourage the student rollouts to explore more regions of the teacher distribution, allowing DMD to provide learning signals beyond the modes already covered by the student. Moreover, the cleaner tokens act as denoising guidance for other noisier tokens, improving the intermediate rollout predictions and reducing error accumulation. Extensive experiments demonstrate that our method improves multiple AR video diffusion distillation methods with higher visual quality efficiently, without incorporating real video data or additional post-training stages.

Related papers

• Generative Video Compression with Adaptive Score Distillation [27.528262844772993]
  We introduce our Generative Video Codec (GenVC), built on a video diffusion model trained from scratch for compression.<n> Experimental results show that GenVC achieves state-of-the-art perceptual quality at ultra-low-FIDs.
  arXiv  Detail & Related papers  (2026-07-24T05:28:30Z)
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators [68.69611976783243]
  OPSD-V is an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models.<n>Key idea is to introduce real long-video data as temporal context during training and use it to provide dense trajectory-level supervision.<n>Experiments show consistent improvements in visual quality, motion dynamics, and VBenchLong scores.
  arXiv  Detail & Related papers  (2026-07-09T17:59:11Z)
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models [49.369312232769154]
  We introduce Causal-rCM, a leading, unified, and scalable algorithm-infrastructure open recipe for diffusion distillation and causal training.<n>We achieve state-of-the-art streaming video generation performance in both frame-wise and chunk-wise settings, using only synthetic data for training.
  arXiv  Detail & Related papers  (2026-06-24T06:58:02Z)
• Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation [25.352409052792122]
  We propose Data-Forcing Distillation (DFD), a simple post-training framework that restores diversity and fidelity in DMD with only a single-line of code change.<n>We provide an in-depth theoretical analysis of our framework and validate our approach on text-to-video, image-to-video, and autoregressive video generation.
  arXiv  Detail & Related papers  (2026-06-16T20:38:30Z)
• SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation [57.297118390628384]
  Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.<n>We propose textbfScore Gradient Matching Distillation (SGMD).<n>It adopts a fake-score perspective by directly optimizing the fake score toward the teacher, while using teacher stop-gradient Fisher as a stable distribution-matching objective.<n>It substantially improves motion dynamics for 4-step distilled models while preserving temporal consistency.
  arXiv  Detail & Related papers  (2026-05-28T15:50:55Z)
• On-Policy Adversarial Flow Distillation for Autoregressive Video Generation [34.70887671905755]
  Adversarial Flow Distillation (AFD) is an on-policy framework for heterogeneous black-box video distillation.<n>AFD queries the teacher and rolls out the current student on the same prompts.<n>AFD provides dense velocity-field supervision while requiring no teacher scores, latents, denoising trajectories, step alignment, or reverse-chain reinforcement learning.
  arXiv  Detail & Related papers  (2026-05-25T17:58:12Z)
• Transition Matching Distillation for Fast Video Generation [63.1049790376783]
  We present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators.<n>TMD matches the multi-step denoising trajectory of a diffusion model with a few-step probability transition process.<n>TMD provides a flexible and strong trade-off between generation speed and visual quality.
  arXiv  Detail & Related papers  (2026-01-14T21:30:03Z)
• Real-Time Motion-Controllable Autoregressive Video Diffusion [79.32730467857535]
  We propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control.<n>We first fine-tune a base I2V model to support basic motion control, then further improve it via reinforcement with a trajectory-based reward model.<n>Our design preserves the Markov property through a Self-Rollout learning mechanism and accelerates training by selectively denoising steps.
  arXiv  Detail & Related papers  (2025-10-09T12:17:11Z)
• Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis [65.77083310980896]
  We propose Adrial Distribution Matching (ADM) to align latent predictions between real and fake score estimators for score distillation.<n>Our proposed method achieves superior one-step performance on SDXL compared to DMD2 while consuming less GPU time.<n>Additional experiments that apply multi-step ADM distillation on SD3-Medium, SD3.5-Large, and CogVideoX set a new benchmark towards efficient image and video synthesis.
  arXiv  Detail & Related papers  (2025-07-24T16:45:05Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [48.35054927704544]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)
• Accelerating Diffusion Models with One-to-Many Knowledge Distillation [35.130782477699704]
  We introduce one-to-many knowledge distillation (O2MKD), which distills a single teacher diffusion model into multiple student diffusion models. Experiments on CIFAR10, LSUN Church, CelebA-HQ with DDPM and COCO30K with Stable Diffusion show that O2MKD can be applied to previous knowledge distillation and fast sampling methods to achieve significant acceleration.
  arXiv  Detail & Related papers  (2024-10-05T15:10:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.