safety-critical applications
- Beyond $\tilde{O}(\sqrt{T})$ Constraint Violation for Online Convex Optimization with Adversarial Constraints
- CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
- Constrained Posterior Sampling: Time Series Generation with Hard Constraints
- Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation