Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference-Aligned Reinforcement Learning on MetaWorld
Loading...
21,000
Label Score
PrefVLM
-320
5,215
10,750
16,285
Jul 2, 2026
Label Score
Image Score
Updated 23d ago
Evaluation Results
Method
Method
Links
Label Score
Image Score
PrefVLM
2026.07
21,000
2,000
RL-VLM-F
2026.07
5,000
10,000
ERL-VLM
2026.07
4,900
4,900
CoRe
2026.07
500
4,000
Feedback
Search any
task
Search any
task
