Kazi Hasan
Ibn Arif

HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models

Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji

PaperCodeDemo

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Models

Kazi Hasan Ibn Arif, Sajib Acharjee Dip, Khizar Hussain, Lang Zhang, Chris Thomas

PaperCode

Equitable Skin Disease Prediction Using Transfer Learning and Domain Adaptation

Sajib Acharjee Dip, Kazi Hasan Ibn Arif, Uddip Acharjee Shuvo, Ishtiaque Ahmed Khan, Na Meng

Paper

Local and Global Feature Based Hybrid Deep Learning Model for Bangla Parts of Speech Tagging

Muntasir Hoq, Kazi Hasan Ibn Arif, Mohammed Nazim Uddin

Paper

Intent-Aware Caching for Efficient LLM Serving

Kazi Hasan Ibn Arif, JinYi Yoon, Dimitrios S. Nikolopoulos, Hans Vandierendonck, Deepu John, Bo Ji

GazeVLM: Gaze-Guided Vision-Language Models for Efficient and Robust Inference

JinYi Yoon, Kazi Hasan Ibn Arif, Bo Ji

Paper

Generate 3D Bone from DICOM using Deep CNN

Kazi Hasan Ibn Arif, Jainta Paul, Dr. Mahmuda Naznin

Paper