JinPLU commited on
Commit
56a90a7
·
verified ·
1 Parent(s): 538b87b

Refresh WRBench Hugging Face narrative

Browse files
Files changed (1) hide show
  1. README.md +17 -11
README.md CHANGED
@@ -10,19 +10,25 @@ short_description: Persistent-state world model benchmark
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
 
 
10
 
11
  # WRBench
12
 
13
+ WRBench is an open benchmark for camera-controlled video world models and
14
+ diagnostic D1-D6 evaluation, introduced in *Current World Models Lack a
15
+ Persistent State Core*.
16
 
17
+ ## Start Here
18
 
 
 
 
 
19
  - Leaderboard: https://huggingface.co/spaces/WRBench/wrbench-leaderboard
20
+ - Results dataset: https://huggingface.co/datasets/WRBench/wrbench-results
21
+ - Benchmark videos: https://huggingface.co/datasets/WRBench/wrbench-videos
22
+ - Natural-25 prompts and first frames: https://huggingface.co/datasets/WRBench/wrbench-natural25
23
+ - Human annotation labels: https://huggingface.co/datasets/WRBench/wrbench-human-annotations
24
+ - Release collection: https://huggingface.co/collections/WRBench/wrbench-current-world-models-lack-a-persistent-state-core
25
 
26
+ The paper reports a frozen benchmark table. The Hugging Face results dataset and
27
+ leaderboard can be refreshed as new public results are released, so current
28
+ model, video, and support counts should be read from the data files.
29
 
30
+ ## Links
31
+
32
+ - Paper: https://arxiv.org/abs/2606.20545
33
+ - Project page: https://jinplu.github.io/WRBench/
34
+ - Code: https://github.com/JinPLu/WRBench