cs.CVNov 2, 2026

OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation

Authors: Zihao Fan, Xin Lu, Jie Huang, Hexin Zhang, Xueyang Fu, Zheng-Jun Zha

Organizations: University of Science and Technology of China

Abstract

Reinforcement learning (RL) elevates joint audio-video generation, but optimizing heterogeneous, modality-specific audio and video rewards often introduces cross-modal interference. On-policy distillation (OPD) alleviates this issue by transferring the capabilities of specialized audio and video RL teachers into a single student model. However, a significant imbalance in cross-modal token counts leaves audio with sparse supervision, causing unstable distillation. We observe that naively increasing the audio loss weight fails to solve this problem since audio learning relies heavily on visual context, indicating richer visual cues are crucial to offset sparse audio signals. To address this, we propose OmniOPD, a modality-wise on-policy distillation framework designed for balanced and stable audio-video generation. First, we construct privileged visual information using asymmetric noise scheduling, allowing the audio teacher to generate more informative targets from cleaner video context. Second, we introduce grouped multi-noise sampling to expand audio supervision coverage and stabilize training. Third, we introduce timestep-wise importance weighting based on teacher-student transition divergence, preserving reliable supervision while down-weighting unreliable learning signals, to stabilize fluctuations in audio learning. Evaluated on JavisBench and VBench demonstrate OmniOPD preserves audio quality while significantly enhancing video generation, achieving effective joint distillation.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation

    May 12, 2026Guohui Zhang, XiaoXiao Ma, Jie Huang +9Audio-Video GenerationAudio-Visual Synchronization

  2. AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

    Sep 24, 2026Zhiyu Xu, Weilong Yan, Yufei Shi +4Audio-Video GenerationAudio-Visual Alignment