wang PRO

xinpeng

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 6 hours ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

submitted a paper about 6 hours ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

updated a dataset 10 months ago

xinpeng/big-math-hard_tiny_instruct_cheat_rm_loophole_v2_mixed_0.5

View all activity

Organizations

upvoted a paper about 6 hours ago

OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation

Paper • 2610.02781 • Published 6 days ago • 4

upvoted a paper over 1 year ago

Refusal Direction is Universal Across Safety-Aligned Languages

Paper • 2505.17306 • Published May 22, 2025 • 2