Peng Wang's picture

In a Training Loop 🔄

Peng Wang

stillarrow

·

https://peter-peng-w.github.io/

AI & ML interests

None yet

Recent Activity

upvoted a paper about 5 hours ago

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

updated a model about 12 hours ago

stillarrow/qwen2.5-math-7b__skill_accuracy_binning_max_entrop-6bc47709-et_mix_lambda_no_drift_off_ratio_100

updated a model about 13 hours ago

stillarrow/qwen2.5-math-7b__skill_accuracy_binning_max_entrop-aabaf976-policy_lambda_no_drift_off_ratio_100

View all activity

Organizations

None yet

stillarrow 's datasets 1

stillarrow/MATH

Viewer • Updated Sep 25, 2025 • 26.5k • 37