5 papers
Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation
Zoe De Simone, Angie Boggust, Fredo Durand +2
Text-to-image (T2I) systems enable rapid generation of high-fidelity imagery but are misaligned with how visual ideas develop. T2I systems generate outputs that make implicit visua…
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
Walid Bousselham, Angie Boggust, Hendrik Strobelt +1
As Vision-Language Models (VLMs) become increasingly sophisticated and widely used, it becomes more and more crucial to understand their decision-making process. Traditional explai…
Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
Angie Boggust, Donghao Ren, Yannick Assogba +3
Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague…
Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
Angie Boggust, Hyemin Bang, Hendrik Strobelt +1
While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to general…
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Walid Bousselham, Angie Boggust, Sofian Chaybouti +2
Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However,…