Dze

xinkekong

5

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 14 days ago

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

upvoted a paper 14 days ago

GLM-5: from Vibe Coding to Agentic Engineering

updated a model 4 months ago

xinkekong/Qwen3-8B-dapo256-rlcr-64

View all activity

Organizations

None yet

upvoted 2 papers 14 days ago

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

Paper • 2605.28293 • Published May 27 • 89

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published Feb 17 • 216

upvoted a paper 4 months ago

TEMPO: Scaling Test-time Training for Large Reasoning Models

Paper • 2604.19295 • Published Apr 21 • 36

upvoted 2 collections 4 months ago

EMPO

8 items • Updated Mar 2 • 3

TEMPO

6 items • Updated May 13 • 1