Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Image-to-Text Style Generation on VLM Dataset
Loading...
97.4
AUC
For-Value
47.064
60.132
73.2
86.268
Aug 13, 2025
AUC
Recall
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUC
Recall
For-Value
VLM Model=Llama-3.2-11...
2025.08
97.4
99.7
For-Value
VLM Model=Qwen2.5-VL-3...
2025.08
89.5
91.6
Emb
VLM Model=Qwen2.5-VL-3...
2025.08
56
19.8
Emb
VLM Model=Llama-3.2-11...
2025.08
55.3
34
DataInf
VLM Model=Qwen2.5-VL-3...
2025.08
52
76
HyperINF
VLM Model=Qwen2.5-VL-3...
2025.08
51.6
86
Hessian-free
VLM Model=Qwen2.5-VL-3...
2025.08
51.5
79.9
Hessian-free
VLM Model=Llama-3.2-11...
2025.08
51.5
82.4
DataInf
VLM Model=Llama-3.2-11...
2025.08
51.5
78.5
HyperINF
VLM Model=Llama-3.2-11...
2025.08
49
82.1
Feedback
Search any
task
Search any
task