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

arXiv:2609.29816 · cs.CV, cs.SD · Submitted 2026-09-24 · Read on arXiv

cs.CV, cs.SD

Submitted: 2026-09-24

Updated: 2026-09-28

Terminology

• GRPO — 49× in this paper · explained in 6 episodes
• Alignment — 27× in this paper · explained in 1 episode
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Audio Quality — 6× in this paper
• Consistency — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Credit assignment — 5× in this paper · explained in 3 episodes
• Semantic Alignment — 5× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Decoupling — 3× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• GRPO Objective — 3× in this paper · explained in 2 episodes
• Visual Quality — 3× in this paper
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptive Noise Clipping — 1× in this paper
• Aggregation — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Dual-Stream Architecture — 1× in this paper · explained in 3 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
• LTX-2: Efficient Joint Audio-Visual Foundation Model
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
• Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• LongCat-Flash-Omni Technical Report
• MOVA: Towards Scalable and Synchronized Video-Audio Generation
• Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
• UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
• DanceGRPO: Unleashing GRPO on Visual Generation
• OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models