# JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation

arXiv: https://arxiv.org/abs/2602.19163 · HTML: https://mlsanity.com/paper/2602.19163/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 79 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Builds on (most cited first, 30 of 68)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [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)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://mlsanity.com/paper/2212.09478/) (2022)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [Any-to-Any Generation via Composable Diffusion](https://mlsanity.com/paper/2305.11846/) (2023)
- [UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining](https://mlsanity.com/paper/2304.09151/) (2023)

## Built on by (most cited first, 25 of 25)

- [OmniForcing: Unleashing Real-time Joint Audio-Visual Generation](https://mlsanity.com/paper/2603.11647/) (2026)
- [MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation](https://mlsanity.com/paper/2605.20183/) (2026)
- [Do Joint Audio-Video Generation Models Understand Physics?](https://mlsanity.com/paper/2605.07061/) (2026)
- [OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation](https://mlsanity.com/paper/2605.12480/) (2026)
- [MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model](https://mlsanity.com/paper/2606.17800/) (2026)
- [InstructAV2AV: Instruction-Guided Audio-Video Joint Editing](https://mlsanity.com/paper/2605.18467/) (2026)
- [VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation](https://mlsanity.com/paper/2608.18607/) (2026)
- [MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation](https://mlsanity.com/paper/2605.28035/) (2026)
- [Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds](https://mlsanity.com/paper/2608.23383/) (2026)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning](https://mlsanity.com/paper/2605.12179/) (2026)
- [Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models](https://mlsanity.com/paper/2607.09091/) (2026)
- [Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency](https://mlsanity.com/paper/2607.11836/) (2026)
- [Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation](https://mlsanity.com/paper/2609.08275/) (2026)
- [MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control](https://mlsanity.com/paper/2606.29473/) (2026)
- [Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence](https://mlsanity.com/paper/2608.10720/) (2026)
- [DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution](https://mlsanity.com/paper/2608.31106/) (2026)
- [The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation](https://mlsanity.com/paper/2609.02367/) (2026)
- [AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation](https://mlsanity.com/paper/2609.06991/) (2026)
- [All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation](https://mlsanity.com/paper/2609.27901/) (2026)
- [AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation](https://mlsanity.com/paper/2609.29816/) (2026)
- [Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy](https://mlsanity.com/paper/2609.34381/) (2026)
- [Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL](https://mlsanity.com/paper/2609.37200/) (2026)
- [Spend Where It Matters: Particle Search with MH Refinement for Budget-Constrained Audio-Visual Alignment](https://mlsanity.com/paper/2610.12811/) (2026)
- [Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generation](https://mlsanity.com/paper/2610.15512/) (2026)

## Abstract (arXiv)

AIGC has rapidly expanded from text-to-image generation toward high-quality multimodal synthesis across video and audio. Within this context, joint audio-video generation (JAVG) has emerged as a fundamental task that produces synchronized and semantically aligned sound and vision from textual descriptions. However, compared with advanced commercial models such as Veo3, existing open-source methods still suffer from limitations in generation quality, temporal synchrony, and alignment with human preferences. To bridge the gap, this paper presents JavisDiT++, a concise yet powerful framework for unified modeling and optimization of JAVG. First, we introduce a modality-specific mixture-of-experts (MS-MoE) design that enables cross-modal interaction efficacy while enhancing single-modal generation quality. Then, we propose a temporal-aligned RoPE (TA-RoPE) strategy to achieve explicit, frame-level synchronization between audio and video tokens. Besides, we develop an audio-video direct preference optimization (AV-DPO) method to align model outputs with human preference across quality, consistency, and synchrony dimensions. Built upon Wan2.1-1.3B-T2V, our model achieves state-of-the-art performance merely with around 1M public training entries, significantly outperforming prior approaches in both qualitative and quantitative evaluations. Comprehensive ablation studies have been conducted to validate the effectiveness of our proposed modules. All the code, model, and dataset are released at https://JavisVerse.github.io/JavisDiT2-page.