HONG SHIBO PRO

SPUH

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

ACWM-RM: A Reference-Free Reward Model from Complementary Mismatch Preferences

liked a model 18 days ago

deepseek-ai/DeepSeek-V4.1-Flash

updated a dataset about 1 month ago

SPUH/DreamDojo_RL

View all activity

Organizations

models 1

SPUH/UFEval

Updated Aug 5, 2025 • 44 • 1

datasets 5

SPUH/DreamDojo_RL

Preview • Updated Oct 12 • 36

SPUH/RM

Updated Oct 7 • 10

SPUH/RM-Training

Preview • Updated Oct 7 • 51

SPUH/DLEBench

Viewer • Updated Apr 3 • 4.4k • 1.51k • 3

SPUH/FRABench

Updated Aug 5, 2025 • 77 • 1