# VibeAvatar: Aligning Phonetic Kinematics and Human Aesthetics for High-Fidelity Talking Avatar Synthesis

arXiv: https://arxiv.org/abs/2609.18632 · HTML: https://mlsanity.com/paper/2609.18632/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 58 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions](https://mlsanity.com/paper/2407.08136/) (2024)
- [AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation](https://mlsanity.com/paper/2403.17694/) (2024)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN](https://mlsanity.com/paper/2203.04036/) (2022)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://mlsanity.com/paper/2411.17440/) (2024)
- [Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer](https://mlsanity.com/paper/2412.00733/) (2024)
- [VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild](https://mlsanity.com/paper/2211.14758/) (2022)
- [Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency](https://mlsanity.com/paper/2409.02634/) (2024)
- [StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator](https://mlsanity.com/paper/2305.05445/) (2023)
- [Goku: Flow Based Video Generative Foundation Models](https://mlsanity.com/paper/2502.04896/) (2025)
- [Wan-S2V: Audio-Driven Cinematic Video Generation](https://mlsanity.com/paper/2508.18621/) (2025)
- [MotionEditor: Editing Video Motion via Content-Aware Diffusion](https://mlsanity.com/paper/2311.18830/) (2023)
- [LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision](https://mlsanity.com/paper/2412.09262/) (2024)

## Abstract (arXiv)

Multi-modal talking avatar synthesis aims to generate realistic talking videos from a reference portrait and speech. Despite rapid progress in diffusion-based methods, existing approaches still struggle to jointly achieve accurate lip articulation, human-preferred motion aesthetics, and efficient inference. We observe that phonetic accuracy and motion aesthetics arise from fundamentally different sources and should be addressed at complementary stages rather than learned implicitly by a single generator. Based on this insight, we propose VibeAvatar, which disentangles these two objectives through a Phonetic Kinematics Adapter (PKA) that converts recognition-oriented speech features into phonetic-kinematic conditions at the conditioning stage, and an Aesthetic Motion Policy (AMP) that optimizes a flow-consistent stochastic sampling policy via Group Relative Policy Optimization (GRPO) at the post-training stage. With a lightweight flow-based motion generator operating in a compact 1D warp-based latent motion space, VibeAvatar achieves state-of-the-art results in articulation, aesthetics, and efficiency on both objective metrics and user studies, while generating a 10-second 512px video in under 10 seconds with only ~3GB VRAM.