Formal Verification of Neural PDE Surrogates Using SMT
Explore formal verification methods for Fourier Neural Operators in PDE surrogates, balancing soundness and scalability for reliable scientific computing.
Self-ReSET: Boost AI Safety with Dynamic Error Recovery
Discover Self-ReSET, a novel framework that enables AI models to self-recover from unsafe reasoning and improve robustness against adversarial attacks.
PnP-Corrector: Boosting Accuracy in Spatiotemporal Forecasting
Discover PnP-Corrector, a universal framework that reduces errors and improves accuracy in coupled spatiotemporal forecasting for climate and ecological sy...
Enhancing Safety in Large Reasoning Models with Verification
Discover how verification improves safety understanding in large reasoning models, reducing risks and boosting secure AI alignment with the SInternal frame...
OPT-BENCH: Quality-Aware RL for NP-Hard Optimization in LLMs
Discover OPT-BENCH, a quality-aware reinforcement learning framework boosting LLMs' success in NP-hard optimization with superior solution quality.