# UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

arXiv: https://arxiv.org/abs/2512.09327 · HTML: https://mlsanity.com/paper/2512.09327/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 60 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 30 of 40)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing](https://mlsanity.com/paper/2011.15126/) (2020)
- [FaceFormer: Speech-Driven 3D Facial Animation with Transformers](https://mlsanity.com/paper/2112.05329/) (2021)
- [MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement](https://mlsanity.com/paper/2104.08223/) (2021)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation](https://mlsanity.com/paper/2303.11089/) (2023)
- [Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion](https://mlsanity.com/paper/2204.08451/) (2022)
- [Generalizable and Animatable Gaussian Head Avatar](https://mlsanity.com/paper/2410.07971/) (2024)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis](https://mlsanity.com/paper/2311.17590/) (2023)
- [DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models](https://mlsanity.com/paper/2310.00434/) (2023)
- [Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition](https://mlsanity.com/paper/1803.09125/) (2018)
- [Imitator: Personalized Speech-driven 3D Facial Animation](https://mlsanity.com/paper/2301.00023/) (2022)
- [GPAvatar: Generalizable and Precise Head Avatar from Image(s)](https://mlsanity.com/paper/2401.10215/) (2024)
- [One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field](https://mlsanity.com/paper/2304.05097/) (2023)
- [SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces](https://mlsanity.com/paper/2306.10799/) (2023)
- [Responsive Listening Head Generation: A Benchmark Dataset and Baseline](https://mlsanity.com/paper/2112.13548/) (2021)
- [Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions](https://mlsanity.com/paper/1901.01874/) (2019)
- [NOFA: NeRF-based One-shot Facial Avatar Reconstruction](https://mlsanity.com/paper/2307.03441/) (2023)
- [Can Language Models Learn to Listen?](https://mlsanity.com/paper/2308.10897/) (2023)
- [Dyadic Interaction Modeling for Social Behavior Generation](https://mlsanity.com/paper/2403.09069/) (2024)
- [DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations](https://mlsanity.com/paper/2505.18096/) (2025)
- [UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model](https://mlsanity.com/paper/2408.00762/) (2024)
- [ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model](https://mlsanity.com/paper/2502.20323/) (2025)
- [High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors](https://mlsanity.com/paper/2211.15064/) (2022)
- [MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset](https://mlsanity.com/paper/2406.14272/) (2024)

## Built on by (most cited first, 11 of 11)

- [LPM 1.0: Video-based Character Performance Model](https://mlsanity.com/paper/2604.07823/) (2026)
- [SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation](https://mlsanity.com/paper/2605.10079/) (2026)
- [ReactMotion: Generating Reactive Listener Motions from Speaker Utterance](https://mlsanity.com/paper/2603.15083/) (2026)
- [EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents](https://mlsanity.com/paper/2604.17211/) (2026)
- [HelloWorld: Enabling Socially Interactive Characters in Video World Models](https://mlsanity.com/paper/2608.05070/) (2026)
- [GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization](https://mlsanity.com/paper/2603.25020/) (2026)
- [FacePlex: Toward Natural Full-Duplex Conversational Avatars](https://mlsanity.com/paper/2606.30145/) (2026)
- [STEER: Steerable Dyadic Head Avatars](https://mlsanity.com/paper/2607.23840/) (2026)
- [InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond](https://mlsanity.com/paper/2609.04903/) (2026)
- [EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold](https://mlsanity.com/paper/2609.35616/) (2026)
- [CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks](https://mlsanity.com/paper/2610.15327/) (2026)

## Abstract (arXiv)

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This failure stems from a fundamental imbalance: the speaker's motion is strongly driven by speech audio, while the listener's motion primarily follows an internal motion prior and is only loosely guided by external speech. This challenge has led most methods to focus on speak-only generation. The only prior attempt at joint generation relies on extra speaker's motion to produce the listener. This design is not end-to-end, thereby hindering the real-time applicability. To address this limitation, we present UniLS, the first end-to-end framework for generating unified speak-listen expressions, driven by only dual-track audio. Our method introduces a novel two-stage training paradigm. Stage 1 first learns the internal motion prior by training an audio-free autoregressive generator, capturing the spontaneous dynamics of natural facial motion. Stage 2 then introduces the dual-track audio, fine-tuning the generator to modulate the learned motion prior based on external speech cues. Extensive evaluations show UniLS achieves state-of-the-art speaking accuracy. More importantly, it delivers up to 44.1% improvement in listening metrics, generating significantly more diverse and natural listening expressions. This effectively mitigates the stiffness problem and provides a practical, high-fidelity audio-driven solution for interactive digital humans. Code and demos are available at https://xg-chu.site/projectunils/.