baohao/aime24
Viewer • Updated • 30 • 350
SAGE
Self-Hinting Language Models Enhance Reinforcement Learning
-
-
baohao/aime25
Viewer • Updated • 30 • 338 -
baohao/amc23
Viewer • Updated • 40 • 297 -
baohao/olympiadbench
Viewer • Updated • 675 • 211 -
baohao/minerva_math
Viewer • Updated • 272 • 216 -
baohao/math500
Viewer • Updated • 500 • 239 -
baohao/gpqa
Viewer • Updated • 198 • 32 -
baohao/mmlu_pro
Viewer • Updated • 12k • 25 -
baohao/sage_train
Viewer • Updated • 15k • 33 -
baohao/luffy_train
Viewer • Updated • 15k • 15 -
baohao/scaf-grpo_train
Viewer • Updated • 15k • 12 -
Self-Hinting Language Models Enhance Reinforcement Learning
Paper • 2602.03143 • Published • 31 -
baohao/sage_validation
Viewer • Updated • 1.67k • 24 -
baohao/SAGE_Llama-3.2-3B-Instruct
4B • Updated • 13 -
baohao/SAGE_Qwen2.5-7B-Instruct
8B • Updated • 29 -
baohao/SAGE_Qwen3-4B-Instruct-2507
4B • Updated • 6 -
baohao/SAGE-light_Qwen2.5-7B-Instruct
8B • Updated • 65 • 2 -
baohao/SAGE-light_Llama-3.2-3B-Instruct
4B • Updated • 3 -
baohao/SAGE-light_Qwen3-4B-Instruct-2507
4B • Updated • 3 -
baohao/SFT_Qwen3-4B-Instruct-2507
4B • Updated • 10 -
baohao/LUFFY_Qwen3-4B-Instruct-2507
4B • Updated • 1.35k -
baohao/GRPO_Qwen3-4B-Instruct-2507
4B • Updated • 758 -
baohao/Scaf-GRPO_Qwen3-4B-Instruct-2507
4B • Updated • 509