wangzixuan

wangzx1210

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 8 days ago

DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation

upvoted a paper about 2 months ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

upvoted a paper 2 months ago

TTPO: Test-Time Policy Optimization

View all activity

Organizations

Papers 3

arxiv:2608.23318

arxiv:2508.05614

arxiv:2505.21500

models 0

None public yet

datasets 1

wangzx1210/OmniEAR

Viewer • Updated Aug 9, 2025 • 30.2k • 510 • 10