Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao
baohao
AI & ML interests
NLP
Recent Activity
updated a model 1 day ago
baohao/Scaf-GRPO_Qwen3-4B-Instruct-2507 updated a collection 1 day ago
SAGE updated a collection 1 day ago
SAGEOrganizations
models 19
baohao/Scaf-GRPO_Qwen3-4B-Instruct-2507
4B • Updated • 342
baohao/GRPO_Qwen3-4B-Instruct-2507
4B • Updated • 671
baohao/LUFFY_Qwen3-4B-Instruct-2507
4B • Updated • 1.06k
baohao/SFT_Qwen3-4B-Instruct-2507
4B • Updated • 10
baohao/hle_sample_trace
Updated
baohao/SAGE-light_Qwen3-4B-Instruct-2507
4B • Updated • 1
baohao/SAGE-light_Llama-3.2-3B-Instruct
4B • Updated • 1
baohao/SAGE-light_Qwen2.5-7B-Instruct
8B • Updated • 522 • 2
baohao/SAGE_Qwen3-4B-Instruct-2507
4B • Updated
baohao/SAGE_Qwen2.5-7B-Instruct
8B • Updated • 279
datasets 26
baohao/hle_rl
Viewer • Updated • 30.1k • 27
baohao/hle_sample_trace
Updated • 17
baohao/sage_validation
Viewer • Updated • 1.67k • 18
baohao/luffy_train
Viewer • Updated • 15k • 12
baohao/sage_train
Viewer • Updated • 15k • 41
baohao/scaf-grpo_train
Viewer • Updated • 15k • 8
baohao/olympiadbench
Viewer • Updated • 675 • 271
baohao/mmlu_pro
Viewer • Updated • 12k • 38
baohao/minerva_math
Viewer • Updated • 272 • 272
baohao/math500
Viewer • Updated • 500 • 285