TAILab-RLMIA

AI & ML interests

Fine-tuned LLM weights with RLVR algorithms for membership inference.

Recent Activity

hanya256  updated a model 25 days ago

RLMIA/MIA-GRPO-VL-Qwen2.5-VL-7b-epoch40

hanya256  updated a model 25 days ago

RLMIA/MIA-GRPO-VL-Qwen2.5-VL-7b-epoch60

hanya256  published a model 25 days ago

RLMIA/MIA-GRPO-VL-Qwen2.5-VL-7b-epoch40

View all activity

Team members 1