← Search

Ada Görgün

2 accepted papers

2026

Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions

ICLR 2026poster

Diffusion models are usually evaluated by their final outputs, gradually denoising random noise into meaningful images. Yet, generation unfolds along a trajectory, and understanding this dynamic process is crucial for explaining how controllable, reliable, and predictable these models are in terms…

Cited by 0SourcecodeScholar
2025

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow

ICCV 2025poster

Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization (FV) is a powerful tool to decode what information neurons ar…