---
title: XPENG AI
emoji: 🚗
colorFrom: gray
colorTo: red
sdk: static
pinned: false
---
## 
XPENG AI
Open-source models and research for intelligent mobility.
[Official Website](https://xpeng-ai.github.io/) · [GitHub](https://github.com/XPENG-AI) · [X-AuT](https://xpeng-ai.github.io/x-aut/) · [OmniGUI](https://omni-gui.github.io/)
---
## About
XPENG AI shares selected models, research, and practical tools with the open-source community. Our work explores efficient AI systems for intelligent mobility, speech, and multimodal interaction.
## Featured Projects
### [X-AuT](https://huggingface.co/XPENG-AI/X-AuT)
**Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation**
X-AuT is a compact automatic speech recognition model based on Qwen3-ASR-0.6B. It reduces the audio encoder from 18 to 14 Transformer blocks through progressive compression and cross-scale knowledge transfer.
The release includes full model weights, standalone inference, and a compact LoRA finetuning example.
| Resource | Link |
| --- | --- |
| Model weights | [XPENG-AI/X-AuT](https://huggingface.co/XPENG-AI/X-AuT) |
| Project website | [xpeng-ai.github.io/x-aut](https://xpeng-ai.github.io/x-aut/) |
| Source code | [XPENG-AI/X-AuT](https://github.com/XPENG-AI/X-AuT) |
### [OmniGUI](https://omni-gui.github.io/)
**Benchmarking GUI Agents in Omni-Modal Smartphone Environments**
OmniGUI is a step-level benchmark for GUI agents operating in smartphone environments with interleaved screenshots, audio, video, and action history. It evaluates localization, semantic understanding, cross-modal discrimination, temporal reasoning, and instant response across 29 applications.
| Resource | Link |
| --- | --- |
| Project website | [omni-gui.github.io](https://omni-gui.github.io/) |
| Paper | [arXiv:2605.18758](https://arxiv.org/abs/2605.18758) |
| Source code | [omni-gui/OmniGUI](https://github.com/omni-gui/OmniGUI) |
| Dataset | [OmniGUI/OmniGUI](https://huggingface.co/datasets/OmniGUI/OmniGUI) |
## More to Come
New models and research projects will be added here as they become publicly available.