Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,28 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: WRBench
|
| 3 |
+
emoji: 🎥
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
short_description: Persistent-state world model benchmark
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# WRBench
|
| 12 |
+
|
| 13 |
+
WRBench is an open benchmark for camera-controlled generation and diagnostic evaluation of video world models, introduced in *Current World Models Lack a Persistent State Core*.
|
| 14 |
+
|
| 15 |
+
## Links
|
| 16 |
+
|
| 17 |
+
- Paper: https://huggingface.co/papers/2606.20545
|
| 18 |
+
- Project page: https://jinplu.github.io/WRBench/
|
| 19 |
+
- GitHub: https://github.com/JinPLu/WRBench
|
| 20 |
+
- Artifact collection: https://huggingface.co/collections/WRBench/wrbench-current-world-models-lack-a-persistent-state-core-6a365c717251293c9fc2cc26
|
| 21 |
+
- Leaderboard: https://huggingface.co/spaces/WRBench/wrbench-leaderboard
|
| 22 |
+
|
| 23 |
+
## Datasets
|
| 24 |
+
|
| 25 |
+
- Natural-25 prompts, variants, and first frames: https://huggingface.co/datasets/WRBench/wrbench-natural25
|
| 26 |
+
- 23-model evaluation results: https://huggingface.co/datasets/WRBench/wrbench-results
|
| 27 |
+
- Human annotation verdicts: https://huggingface.co/datasets/WRBench/wrbench-human-annotations
|
| 28 |
+
- Benchmark videos and per-video scores: https://huggingface.co/datasets/WRBench/wrbench-videos
|