collaborators

9 papers

cs.CV2026

Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning

Taha Koleilat, Hassan Rivaz, Yiming Xiao

Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing methods remain deterministic…

cs.CV2026

CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values

Taha Koleilat, Hassan Rivaz, Yiming Xiao

Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-g…

cs.CV2026

Sparse Spectral LoRA: Routed Experts for Medical VLMs

Omid Nejati Manzari, Hojat Asgariandehkordi, Taha Koleilat +2

Large vision-language models (VLMs) excel on general benchmarks but often lack robustness in medical imaging, where heterogeneous supervision induces cross-dataset interference and…

cs.CV2026

MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation

Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari +3

Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP…

cs.CV2025

Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention

Omid Nejati Manzari, Hojat Asgariandehkordi, Taha Koleilat +2

Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However,…

cs.CV2025

Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models

Hamza Rasaee, Taha Koleilat, Hassan Rivaz

Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated…