7 papers
Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs
Shayan Mohammadizadehsamakosh, Pritam Sarkar, Leonid Sigal +2
Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and mis…
Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
Mohammed Saidul Islam, Negin Baghbanzadeh, Farnaz Kohankhaki +5
Evaluation of foundation models often rely on aggregate scores from benchmarks that lack comprehensive coverage and metadata for a fine-grained evaluation. We introduce a framework…
Open-PMC-18M: A High-Fidelity Large Scale Medical Dataset for Multimodal Representation Learning
Negin Baghbanzadeh, Mohammed Saidul Islam, Sajad Ashkezari +2
In biomedical vision-language modeling, datasets are typically mined from scientific literature, pairing compound figures with captions that are short, context-dependent, and ofter…
Consistency-Guided Asynchronous Contrastive Tuning for Few-Shot Class-Incremental Tuning of Foundation Models
Shuvendu Roy, Elham Dolatabadi, Arash Afkanpour +1
We propose Consistency-guided Asynchronous Contrastive Tuning (CoACT), a novel method for continuously tuning foundation models to learn new classes in few-shot settings. CoACT con…
A Flexible Fairness Framework with Surrogate Loss Reweighting for Addressing Sociodemographic Disparities
Wen Xu, Elham Dolatabadi
This paper presents a new algorithmic fairness framework called - Fair Machine Learning (- FML), designed to optimize fa…
Advancing Medical Representation Learning Through High-Quality Data
Negin Baghbanzadeh, Adibvafa Fallahpour, Yasaman Parhizkar +8
Despite the growing scale of medical Vision-Language datasets, the impact of dataset quality on model performance remains under-explored. We introduce Open-PMC, a high-quality medi…