9 papers
Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models
Huichan Seo, Minki Hong, Sieun Choi +2
Instruction-guided image-to-image (I2I) editors are increasingly used in consumer and professional visual workflows, where trustworthiness depends not only on prompt compliance but…
Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
Huichan Seo, Sieun Choi, Minki Hong +8
Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image…
StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback
Jiho Park, Sieun Choi, Jaeyoon Seo +1
Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizing pixel-based human-drawn sketches, a…
PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses
Minki Hong, Eunsoo Lee, Sohyun Park +1
Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt suc…
Before We Trust Them: Decision-Making Failures in Navigation of Foundation Models
Jua Han, Jaeyoon Seo, Jungbin Min +4
High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on s…
SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering
Jiho Park, Sieun Choi, Jaeyoon Seo +3
A sketch is a distilled form of visual abstraction that conveys core concepts through simplified yet purposeful strokes while omitting extraneous detail. Despite its expressive pow…