TAILab-RLMIA

community

AI & ML interests

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

RLMIA 's models 21

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

8B • Updated Sep 11, 2025 • 5

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

8B • Updated Sep 11, 2025 • 5

RLMIA/MIA-DAPO-VL-Qwen2.5-VL-3b-epoch40

4B • Updated Sep 11, 2025 • 4

RLMIA/MIA-DAPO-VL-Qwen2.5-VL-3b-epoch80

4B • Updated Sep 11, 2025 • 6

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

8B • Updated Sep 11, 2025 • 5

RLMIA/MIA-DAPO-VL-Qwen2.5-VL-7b-epoch80

8B • Updated Sep 11, 2025 • 4

RLMIA/MIA-DAPO-MATH-Qwen2.5-3b-epoch20

3B • Updated Sep 11, 2025 • 6

RLMIA/MIA-DAPO-MATH-Qwen2.5-3b-epoch40

3B • Updated Sep 11, 2025 • 5

RLMIA/MIA-DAPO-MATH-Qwen2.5-7b-epoch20

8B • Updated Sep 11, 2025 • 5

RLMIA/MIA-DAPO-MATH-Qwen2.5-7b-epoch40

8B • Updated Sep 11, 2025 • 5

RLMIA/MIA-GRPO-MATH-Qwen2.5-3b-epoch20

3B • Updated Sep 9, 2025 • 4

RLMIA/MIA-GRPO-MATH-Qwen2.5-3b-epoch40

3B • Updated Sep 9, 2025 • 3

RLMIA/MIA-GRPO-MATH-Qwen2.5-3b-epoch60

3B • Updated Sep 9, 2025 • 5

RLMIA/MIA-GRPO-MATH-Qwen2.5-7b-epoch20

8B • Updated Sep 9, 2025 • 6

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

8B • Updated Sep 9, 2025 • 5

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

8B • Updated Sep 9, 2025 • 3

RLMIA/MIA-DAPO-MATH-Qwen2.5-3b-epoch60

3B • Updated Sep 9, 2025 • 4

RLMIA/MIA-DAPO-MATH-Qwen2.5-7b-epoch60

8B • Updated Sep 9, 2025 • 5

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

8B • Updated Sep 9, 2025 • 5

RLMIA/MIA-DAPO-VL-Qwen2.5-VL-3b-epoch60

Updated Sep 9, 2025

RLMIA/MIA-GRPO-VL-Qwen2.5-VL-3b-epoch60

Updated Sep 9, 2025