Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,27 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# NU · World Model & Embodied AI
|
| 11 |
+
|
| 12 |
+
We build and benchmark **world models, embodied agents, and world–action
|
| 13 |
+
models** — systems that simulate, predict, and act in the physical world.
|
| 14 |
+
Our public releases include video generation benchmarks, robot policies,
|
| 15 |
+
action models, and the datasets and judges that hold them to a physical
|
| 16 |
+
standard.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## Current release: Phyground
|
| 21 |
+
|
| 22 |
+
**Phyground** is a benchmark for the *physical plausibility* of
|
| 23 |
+
text-and-image-to-video (ti2v) generations.
|
| 24 |
+
|
| 25 |
+
| Artifact | Link |
|
| 26 |
+
| --- | --- |
|
| 27 |
+
| 📦 Dataset |
|
| 28 |
+
[`phyground`](https://huggingface.co/datasets/NU-World-Model-Embodied-AI/phyground) |
|
| 29 |
+
| 🧑⚖️Judge model |
|
| 30 |
+
[`phyjudge-9B`](https://huggingface.co/NU-World-Model-Embodied-AI/phyjudge-9B) |
|
| 31 |
+
|
| 32 |
+
More releases — robot policies, world–action models, and additional
|
| 33 |
+
benchmarks — are on the way.
|