model reliability
Model reliability encompasses the trustworthiness and consistency of a model's predictions, ensuring that it performs well across different scenarios and maintains its accuracy over time.
- Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
- Information Retrieval Induced Safety Degradation in AI Agents
- Large language models can learn and generalize steganographic chain-of-thought under process supervision
- PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
- Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
- Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
- Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
- What Does It Take to Build a Performant Selective Classifier?