Author

Yi Wang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Review Oct 2026

Differential Privacy Protected Preference Alignment on Survey Derived Data

Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about political beliefs, social norms, religion, gender attitudes, and cultural values. This paper studies privacy-preserving alignment on questionnai...

Xiu-Yuan Qi, Yi Wang, Wen-Jie Wang · 0 citations

#machine learning Preprint Oct 2026

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

Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation steps. Despite their promise, effective post-training of LoopLMs remains challenging. Existing approaches either provide reward based supervision that is sparse or costly...

Yi Wang, Rui Qian, Yu Li et al. · 0 citations