TAILab-RLMIA

community

AI & ML interests

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

Recent Activity

hanya256 updated a model about 1 month ago

RLMIA/GRPO-7B-INSTRUCTION-FOLLOWING

hanya256 published a model about 1 month ago

RLMIA/GRPO-3B-TOOL-USING

hanya256 published a model about 1 month ago

RLMIA/GRPO-3B-SEARCH-R1

View all activity

models 18

RLMIA/GRPO-7B-INSTRUCTION-FOLLOWING

8B • Updated Aug 6 • 3

RLMIA/GRPO-3B-TOOL-USING

3B • Updated Aug 6 • 2

RLMIA/GRPO-3B-SEARCH-R1

Text Generation • 3B • Updated Aug 6 • 14

RLMIA/GRPO-3B-INSTRUCTION-FOLLOWING

3B • Updated Aug 6 • 3

RLMIA/DAPO-7B-VLM-GEO3K

8B • Updated Aug 6 • 6

RLMIA/GRPO-7B-VLM-GEO3K

8B • Updated Aug 6 • 8

RLMIA/DAPO-7B-MATH-SHADOW-HARD

8B • Updated Aug 5 • 6

RLMIA/DAPO-3B-MATH-SHADOW-HARD

3B • Updated Aug 5 • 2

RLMIA/GRPO-7B-MATH-SHADOW-HARD

8B • Updated Aug 5 • 3

RLMIA/GRPO-3B-MATH-SHADOW-HARD

3B • Updated Aug 5 • 3

datasets 0

None public yet