README.md

---
title: XPENG AI
emoji: 🚗
colorFrom: gray
colorTo: red
sdk: static
pinned: false
---

## <img src="https://xpeng-ai.github.io/assets/xpeng-favicon.png?v=2" width="52" alt="XPENG AI logo" align="center"> XPENG AI

Open-source models and research for intelligent mobility.<br>
[Official Website](https://xpeng-ai.github.io/) · [GitHub](https://github.com/XPENG-AI) · [GroundingPI](https://groundingpi.github.io/) · [GroundAnything](https://groundingpi.github.io/groundanything/) · [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

### [GroundingPI](https://huggingface.co/GroundingPI/GroundingPI)

**A Grounding Foundation Model towards Physical Intelligence with Visual Primitives**

GroundingPI is a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. It sets a new state of the art across 34 grounding benchmarks (averaging 73.68%, above GPT-6 Astra) and improves robot manipulation and autonomous driving when used as the visual backbone.

| Resource | Link |
| --- | --- |
| Model weights | [GroundingPI/GroundingPI](https://huggingface.co/GroundingPI/GroundingPI) |
| Online demo | [GroundingPI/GroundingPI Space](https://huggingface.co/spaces/GroundingPI/GroundingPI) |
| Project website | [groundingpi.github.io](https://groundingpi.github.io/) |
| Paper | [arXiv:2609.39601](https://arxiv.org/abs/2609.39601) |
| Source code | [groundingpi/GroundingPI](https://github.com/groundingpi/GroundingPI) |

### [GroundAnything](https://huggingface.co/GroundingPI/GroundAnything-VLM)

**Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed**

GroundAnything combines parallel decoding with precise visual grounding for flash-speed inference. It is released in two variants: a diffusion model ([GroundAnything](https://huggingface.co/GroundingPI/GroundAnything)) and an autoregressive VLM ([GroundAnything-VLM](https://huggingface.co/GroundingPI/GroundAnything-VLM)), with an interactive [demo Space](https://huggingface.co/spaces/GroundingPI/GroundAnything-VLM).

| Resource | Link |
| --- | --- |
| Model weights (VLM) | [GroundingPI/GroundAnything-VLM](https://huggingface.co/GroundingPI/GroundAnything-VLM) |
| Model weights (DLM) | [GroundingPI/GroundAnything](https://huggingface.co/GroundingPI/GroundAnything) |
| Project website | [groundingpi.github.io/groundanything](https://groundingpi.github.io/groundanything/) |
| Paper | [arXiv:2609.39600](https://arxiv.org/abs/2609.39600) |
| Source code | [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything) |

### [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/) |
| Paper | [arXiv:2609.11412](https://arxiv.org/abs/2609.11412) |
| 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.