reliability
Reliability in AI denotes the consistency and dependability of an AI system's performance across various conditions and inputs. A reliable model produces accurate and stable outcomes, making it suitable for deployment in critical applications like healthcare or transportation.
- AliO: Output Alignment Matters in Long-Term Time Series Forecasting
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
- GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
- Measuring AI Ability to Complete Long Software Tasks
- Prohibiting Generative AI in any Form of Weapon Control
- Secure and Confidential Certificates of Online Fairness
- Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation
- Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health
- The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
- Torch-Uncertainty: Deep Learning Uncertainty Quantification
- Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
- Variational Uncertainty Decomposition for In-Context Learning
- What Really is a Member? Discrediting Membership Inference via Poisoning