#Interpretability

4 articles with this tag

MMDiff: Auditing and Steering MLLMs
AI Research

MMDiff: Auditing and Steering MLLMs

MMDiff, a new multimodal model-diffing framework, enables granular control and understanding of MLLMs by isolating and manipulating specific behavioral features.

about 2 months ago
Hybrid AI Models Get Orthogonal
AI Research

Hybrid AI Models Get Orthogonal

OrthoReg, a novel regularization method, ensures clear separation between symbolic and neural components in hybrid dynamical systems, boosting interpretability and generalization.

3 months ago
Phase Dominance in AI Image Recognition
AI Research

Phase Dominance in AI Image Recognition

AI image classifiers exhibit a striking phase dominance for identity encoding, mirroring human vision principles, with architectural differences shaping its expression.

3 months ago
Certified Circuits for Stable AI Explanations
AI Research

Certified Circuits for Stable AI Explanations

New 'Certified Circuits' framework provides provable stability for AI model explanations, yielding more accurate and compact circuits.

7 months ago