collaborators

6 papers

cs.CV2026

See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment

Mohammad Anas Azeez, Ankan Deria, Zohaib Hasan Siddiqui +5

Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding is disproportionately drawn t…

cs.CV2026

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs

Govinda Kolli, Adinath Madhavrao Dukre, Behzad Bozorgtabar +2

Medical Vision-Language Models (VLMs) often hallucinate by generating responses based on language priors rather than visual evidence, posing risks in clinical applications. We prop…

eess.IV2026

TuLaBM: Tumor-Biased Latent Bridge Matching for Contrast-Enhanced MRI Synthesis

Atharva Rege, Adinath Madhavrao Dukre, Numan Balci +2

Contrast-enhanced magnetic resonance imaging (CE-MRI) plays a crucial role in brain tumor assessment; however, its acquisition requires gadolinium-based contrast agents (GBCAs), wh…

cs.CV2026

MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images

Ankan Deria, Komal Kumar, Adinath Madhavrao Dukre +3

Multimodal large language models have advanced rapidly, but their adoption in medicine is constrained by limited domain coverage, imperfect modality alignment, and insufficient gro…

cs.CV2025

Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization

Adinath Dukre, Ankan Deria, Yutong Xie +1

Atypical mitotic figures are important biomarkers of tumor aggressiveness in histopathology, yet reliable recognition remains challenging due to severe class imbalance and variabil…

cs.CV2025

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang +5

Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-con…