Alex's picture

2 2 1

Alex

ShiningMaker

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

upvoted a paper 12 days ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

new activity 6 months ago

meituan/DeepSeek-R1-Block-INT8:After deploying with the latest sglang, I found that the responses when calling the interface were chaotic.

View all activity

Organizations

None yet

upvoted a paper 5 days ago

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Paper • 2508.21104 • Published 10 days ago • 28

upvoted a paper 12 days ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published 18 days ago • 117