👋 Open to Work

Yi Wang

wanglne

·

https://wanglne.github.io/

wanglne

AI & ML interests

None yet

Recent Activity

authored a paper 2 days ago

Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models

authored a paper 2 days ago

Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models

upvoted a paper 2 days ago

Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models

View all activity

Organizations

wanglne 's papers 4

arxiv:2610.10623

arxiv:2610.10625

arxiv:2605.14750

arxiv:2502.11647