Author

Wanyu Lin

h-index 4 View on Semantic Scholar

We have 2 of 12 papers

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.

Sep 2026

Bias Mitigation in Federated Learning Through Feature Integration

Machine learning models are trained on datasets where undesired features have spurious correlations with the target variable, resulting in the bias shifts of the model output to a different class. In federated learning (FL), a common problem is data distribution skew. Since each client has a different distribution, mod...

Zi-Yi Zhang, Ming-Xuan Ouyang, Kun-Hao Li et al. · ACM Transactions on Knowledg... · 0 citations

Preprint Jul 2026

Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation

This work proposes LLMol, a principled reinforcement learning framework that directly incorporates verifiable rewards for targeted molecule generation and introduces Reinforcement Learning with Verifiable Rewards (RLVR), which directly integrates property-based reward signals to guide molecular generation toward task-s...

Mingxuan Ouyang, Hao Lan, Wanyu Lin · 0 citations