Commit 路
0280b6a
1
Parent(s): 06fcb65
Feature AUGUstus after GroundAnything in organization card
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ pinned: false
|
|
| 10 |
## <img src="https://xpeng-ai.github.io/assets/xpeng-favicon.png?v=2" width="52" alt="XPENG AI logo" align="center"> XPENG AI
|
| 11 |
|
| 12 |
Open-source models and research for intelligent mobility.<br>
|
| 13 |
-
[Official Website](https://xpeng-ai.github.io/) 路 [GitHub](https://github.com/XPENG-AI) 路 [GroundingPI](https://groundingpi.github.io/) 路 [GroundAnything](https://groundingpi.github.io/groundanything/) 路 [X-AuT](https://xpeng-ai.github.io/x-aut/) 路 [OmniGUI](https://omni-gui.github.io/)
|
| 14 |
|
| 15 |
---
|
| 16 |
|
|
@@ -48,6 +48,18 @@ GroundAnything combines parallel decoding with precise visual grounding for flas
|
|
| 48 |
| Paper | [arXiv:2609.39600](https://arxiv.org/abs/2609.39600) |
|
| 49 |
| Source code | [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything) |
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### [X-AuT](https://huggingface.co/XPENG-AI/X-AuT)
|
| 52 |
|
| 53 |
**Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation**
|
|
|
|
| 10 |
## <img src="https://xpeng-ai.github.io/assets/xpeng-favicon.png?v=2" width="52" alt="XPENG AI logo" align="center"> XPENG AI
|
| 11 |
|
| 12 |
Open-source models and research for intelligent mobility.<br>
|
| 13 |
+
[Official Website](https://xpeng-ai.github.io/) 路 [GitHub](https://github.com/XPENG-AI) 路 [GroundingPI](https://groundingpi.github.io/) 路 [GroundAnything](https://groundingpi.github.io/groundanything/) 路 [AUGUstus](https://augustus-ad.github.io/) 路 [X-AuT](https://xpeng-ai.github.io/x-aut/) 路 [OmniGUI](https://omni-gui.github.io/)
|
| 14 |
|
| 15 |
---
|
| 16 |
|
|
|
|
| 48 |
| Paper | [arXiv:2609.39600](https://arxiv.org/abs/2609.39600) |
|
| 49 |
| Source code | [groundingpi/GroundAnything](https://github.com/groundingpi/GroundAnything) |
|
| 50 |
|
| 51 |
+
### AUGUstus
|
| 52 |
+
|
| 53 |
+
**Autonomous Driving VLA Model with Unified Generation and Understanding**
|
| 54 |
+
|
| 55 |
+
AUGUstus unifies diffusion-based action generation and autoregressive chain-of-thought understanding in a single VLA model for autonomous driving. It reaches 94.6 PDMS on NAVSIMv1 and 90.7 EPDMS on NAVSIMv2, and has been deployed on a real vehicle running at 12 Hz.
|
| 56 |
+
|
| 57 |
+
| Resource | Link |
|
| 58 |
+
| --- | --- |
|
| 59 |
+
| Project website | [augustus-ad.github.io](https://augustus-ad.github.io/) |
|
| 60 |
+
| Paper | [arXiv:2610.16985](https://arxiv.org/abs/2610.16985) |
|
| 61 |
+
| Source code | [haha-yuki-haha/AUGUstus](https://github.com/haha-yuki-haha/AUGUstus) |
|
| 62 |
+
|
| 63 |
### [X-AuT](https://huggingface.co/XPENG-AI/X-AuT)
|
| 64 |
|
| 65 |
**Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation**
|