10 papers
CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space
Hung Q. Vo, Huy Q. Vo, Son T. Ly +6
Conventional tissue image analysis software provides foundational capabilities for cellular analysis, including segmentation, basic morphological feature extraction, and spatial or…
SketchVLM: Vision language models can annotate images to explain thoughts and guide users
Brandon Collins, Logan Bolton, Hung Huy Nguyen +3
When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models (VLMs) such as Gemini-3-Pro an…
Understanding Generative AI Capabilities in Everyday Image Editing Tasks
Mohammad Reza Taesiri, Brandon Collins, Logan Bolton +4
Generative AI (GenAI) holds significant promise for automating everyday image editing tasks, especially following the recent release of GPT-4o on March 25, 2025. However, what subj…
B-score: Detecting biases in large language models using response history
An Vo, Mohammad Reza Taesiri, Daeyoung Kim +1
Large language models (LLMs) often exhibit strong biases, e.g, against women or in favor of the number 7. We investigate whether LLMs would be able to output less biased answers wh…
Vision Language Models are Biased
An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri +3
Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may notoriously sway their outputs towards wro…
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Tin Nguyen, Logan Bolton, Mohammad Reza Taesiri +2
An Achilles heel of Large Language Models (LLMs) is their tendency to hallucinate non-factual statements. A response mixed of factual and non-factual statements poses a challenge f…
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Jonathan Roberts, Mohammad Reza Taesiri, Ansh Sharma +31
Large Multimodal Models (LMMs) exhibit shortfalls when interpreting images and, by some measures, have poorer spatial cognition than young children or animals. Despite this, they a…
Vision language models are blind: Failing to translate detailed visual features into words
Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri +1
While large language models with vision capabilities (VLMs), e.g., GPT-4o and Gemini 1.5 Pro, score high on many vision-understanding benchmarks, they are still struggling with low…
Allowing humans to interactively guide machines where to look does not always improve human-AI team's classification accuracy
Giang Nguyen, Mohammad Reza Taesiri, Sunnie S. Y. Kim +1
Via thousands of papers in Explainable AI (XAI), attention maps \cite{vaswani2017attention} and feature importance maps \cite{bansal2020sam} have been established as a common means…
GlitchBench: Can large multimodal models detect video game glitches?
Mohammad Reza Taesiri, Tianjun Feng, Anh Nguyen +1
Large multimodal models (LMMs) have evolved from large language models (LLMs) to integrate multiple input modalities, such as visual inputs. This integration augments the capacity…