# OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation

arXiv: https://arxiv.org/abs/2605.12480 · HTML: https://mlsanity.com/paper/2605.12480/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 43 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [DiffusionNFT: Online Diffusion Reinforcement with Forward Process](https://mlsanity.com/paper/2509.16117/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE](https://mlsanity.com/paper/2507.21802/) (2025)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners](https://mlsanity.com/paper/2402.17723/) (2024)
- [FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds](https://mlsanity.com/paper/2407.01494/) (2024)
- [Synchformer: Efficient Synchronization from Sparse Cues](https://mlsanity.com/paper/2401.16423/) (2024)
- [TempFlow-GRPO: When Timing Matters for GRPO in Flow Models](https://mlsanity.com/paper/2508.04324/) (2025)
- [JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization](https://mlsanity.com/paper/2503.23377/) (2025)

## Built on by (most cited first, 7 of 7)

- [VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation](https://mlsanity.com/paper/2608.18607/) (2026)
- [Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions](https://mlsanity.com/paper/2606.09150/) (2026)
- [DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution](https://mlsanity.com/paper/2608.31106/) (2026)
- [AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation](https://mlsanity.com/paper/2609.29816/) (2026)
- [Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL](https://mlsanity.com/paper/2609.37200/) (2026)
- [Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation](https://mlsanity.com/paper/2610.05608/) (2026)
- [From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation](https://mlsanity.com/paper/2610.11770/) (2026)

## Abstract (arXiv)

Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synchronization. Reinforcement Learning (RL) offers a promising paradigm, but its extension to multi-objective and multi-modal joint audio-video generation remains unexplored. Notably, our in-depth analysis first reveals that the primary obstacles to applying RL in this stem from: (i) multi-objective advantages inconsistency, where the advantages of multimodal outputs are not always consistent within a group; (ii) multi-modal gradients imbalance, where video-branch gradients leak into shallow audio layers responsible for intra-modal generation; (iii) uniform credit assignment, where fine-grained cross-modal alignment regions fail to get efficient exploration. These shortcomings suggest that vanilla RL fine-tuning strategy with a single global advantage often leads to suboptimal results. To address these challenges, we propose OmniNFT, a novel modality-aware online diffusion RL framework with three key innovations: (1) Modality-wise advantage routing, which routes independent per-reward advantages to their respective modality generation branches. (2) Layer-wise gradient surgery, which selectively detaches video-branch gradients on shallow audio layers while retaining those for cross-modal interaction layers. (3) Region-wise loss reweighting, which modulates policy optimization toward critical regions related to audio-video synchronization and fine-grained alignment. Extensive experiments on JavisBench and VBench with the LTX-2 backbone demonstrate that OmniNFT achieves comprehensive improvements in audio and video perceptual quality, cross-modal alignment, and audio-video synchronization.