Tag: AI robustness
Browse our exclusive articles!
Adaptive Gaussian Calibration for Multi-modal Test-time Adaptation
Improve multi-modal model accuracy with adaptive probabilistic Gaussian calibration, addressing modality asymmetry during test-time adaptation.
ProjLens: Enhancing Safety in Multimodal Models
Discover how ProjLens improves multimodal model safety by exposing backdoor vulnerabilities and boosting robustness in large language models.
ARES: Enhancing AI Safety with Adaptive Red-Teaming
Discover how ARES improves AI safety by adaptive red-teaming and repairing policy-reward systems in large language models.
LLM Robustness to Chain-of-Thought Perturbations Explained
Explore how large language models handle chain-of-thought perturbations and improve reasoning accuracy across diverse error types.
Early Visual Cortex Alignment Reduces Vision-Language Model Manipulation
Discover how aligning vision-language models with early visual cortex activity helps prevent sycophantic manipulation and enhances AI robustness.