# A2-LLM: An End-to-end Conversational Audio Avatar Large Language Model

arXiv: https://arxiv.org/abs/2602.04913 · HTML: https://mlsanity.com/paper/2602.04913/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 30 of 36)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation](https://mlsanity.com/paper/2406.08801/) (2024)
- [VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time](https://mlsanity.com/paper/2404.10667/) (2024)
- [CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior](https://mlsanity.com/paper/2301.02379/) (2023)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis](https://mlsanity.com/paper/2404.04104/) (2024)
- [Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction](https://mlsanity.com/paper/2502.11946/) (2025)
- [DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models](https://mlsanity.com/paper/2310.00434/) (2023)
- [LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis](https://mlsanity.com/paper/2505.02625/) (2025)
- [Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction](https://mlsanity.com/paper/2502.17239/) (2025)
- [EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions](https://mlsanity.com/paper/2409.18042/) (2024)
- [Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation](https://mlsanity.com/paper/2406.07867/) (2024)

## Built on by (most cited first, 1 of 1)

- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)

## Abstract (arXiv)

Developing expressive and responsive conversational digital humans is a cornerstone of next-generation human-computer interaction. While large language models (LLMs) have significantly enhanced dialogue capabilities, most current systems still rely on cascaded architectures that connect independent modules. These pipelines are often plagued by accumulated errors, high latency, and poor real-time performance. Lacking access to the underlying conversational context, these pipelines inherently prioritize rigid lip-sync over emotional depth. To address these challenges, we propose A2-LLM, an end-to-end conversational audio avatar large language model that jointly reasons about language, audio prosody, and 3D facial motion within a unified framework. To facilitate training, we introduce FLAME-QA, a high-quality multimodal dataset designed to align semantic intent with expressive facial dynamics within a QA format. By leveraging deep semantic understanding, A2-LLM generates emotionally rich facial movements beyond simple lip-synchronization. Experimental results demonstrate that our system achieves superior emotional expressiveness while maintaining real-time efficiency (500 ms latency, 0.7 RTF).