Wenkang Wang — accepted AI-conference papers

2026

Online Black-Box Prompt Optimization with Regret Guarantees under Noisy Feedback

Jinjie Fang, Runwen You, Wanli Shi, Wenkang Wang, Ganyu Wang, Haozhen Zhang +2

ICLR 2026poster

Generative AI excels in various tasks through advanced language modeling techniques, with its performance heavily influenced by input prompts. This has driven significant research into prompt optimization, particularly in commercial generative AI platforms, where prompt optimization is treated as a…

Cited by 0 Source ↗Scholar ↗

2026

Towards Nonlinear Sparse AUC Maximization via Compositional Stochastic Hard Thresholding

Wenkang Wang, Dongxu Liu, Bin Gu

AAAI 2026technical

The Area Under the ROC Curve (AUC) is an important evaluation metric for both linear and, in particular, nonlinear classification models, owing to its robustness against class imbalance. Sparse learning with an ℓ₀ constraint can enhance model interpretability and generalization. Prior work has shown

Cited by 0 Source ↗PDF ↗Scholar ↗