Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,24 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# AceAction Research
|
| 11 |
+
|
| 12 |
+
**Learning to Act in Interactive Worlds.**
|
| 13 |
+
|
| 14 |
+
AceAction is a research initiative exploring how intelligent agents understand goals, perceive dynamic environments, and translate intentions into actions. Our interests span **vision-language-action (VLA) learning**, **action-conditioned world modeling**, and **long-horizon decision-making** in interactive 3D worlds.
|
| 15 |
+
|
| 16 |
+
## 馃搫 Papers
|
| 17 |
+
|
| 18 |
+
### AceAction-5M 路 arXiv 2026
|
| 19 |
+
|
| 20 |
+
**Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds**
|
| 21 |
+
|
| 22 |
+
A multi-game action-learning dataset with hierarchically structured goals, subgoals, and skills across **42 games** and over **5 million annotated episodes**.
|
| 23 |
+
|
| 24 |
+
[Paper](https://arxiv.org/abs/2611.04241)
|
| 25 |
+
|
| 26 |
+
### 3A-VLA 路 NeurIPS 2026
|
| 27 |
+
|
| 28 |
+
**Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds**
|
| 29 |
+
|
| 30 |
+
[Paper](https://arxiv.org/abs/2602.02212)
|