works on

From the 1 of 10 linked papers with an AI index.

collaborators

10 papers

cs.CL2026

StanceMoE: Mixture-of-Experts Architecture for Stance Detection

Abdullah Al Shafi, Md. Milon Islam, Sk. Imran Hossain +1

The paper introduces StanceMoE, a Mixture-of-Experts model built on BERT that dynamically combines specialized expert modules to improve actor-level stance detection in text.

cs.CV2026

Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion

Abdullah Al Shafi, Sumaiya Rahim Suma

Deploying classifier-free guidance (CFG) diffusion models under real-world compute budgets requires quantization, yet existing post-training quantization (PTQ) methods treat CFG mo…

cs.CV2026

BTI-Net: Bidirectional Decoder-Level Task Interaction via Uncertainty-Aware Gating for Multi-Task Medical Image Analysis

Abdullah Al Shafi, Md Kawsar Mahmud Khan Zunayed, Safin Ahmmed +2

Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations,…

cs.CV2026

DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain +1

Parameter compression of class-conditional diffusion models reveals an underexplored limitation in output-level distillation: the unconditional score branch remains unsupervised, l…

cs.CV2026

iPhoneBlur: A Difficulty-Stratified Benchmark for Consumer Device Motion Deblurring

Abdullah Al Shafi, Kazi Saeed Alam

Motion blur restoration on consumer mobile devices is typically evaluated using aggregate metrics that obscure performance variation across blur difficulty, masking model behavior…

cs.CL2026

BiST: A Gold Standard Bangla-English Bilingual Corpus for Sentence Structure and Tense Classification with Inter-Annotator Agreement

Abdullah Al Shafi, Swapnil Kundu Argha, M. A. Moyeen +2

High-quality bilingual resources remain a critical bottleneck for advancing multilingual NLP in low-resource settings, particularly for Bangla. To mitigate this gap, we introduce B…