← Search

Abdul Wasi

2 accepted papers

2026

FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants

CVPR 2026

While powerful in image-conditioned generation, multimodal large language models (MLLMs) can display uneven performance across demographic groups, highlighting fairness risks. In safety-critical clinical settings, such disparities risk producing unequal diagnostic narratives and eroding trust in AI-

Cited by 0SourcecodeScholar
2025

PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions

ICCV 2025poster

Diffusion-based generative models have shown promise in synthesizing histopathology images to address data scarcity caused by privacy constraints. Diagnostic text reports provide high-level semantic descriptions, and masks offer fine-grained spatial structures essential for representing distinct mor…