5 papers
Frozen but Not Always Accessible: A Representation Analysis of Genomic Language Models
Nirjhor Datta, Swakkhar Shatabda, M. Sohel Rahman
Genomic foundation models are increasingly reused as frozen feature extractors for downstream sequence prediction, offering a compute-efficient alternative to full fine-tuning. How…
Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations
Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel Rahman
Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-poin…
DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation
H. M. Shadman Tabib, Md. Shamsuzzoha Bayzid, M Sohel Rahman
Foundation segmentation models such as Segment Anything Model (SAM) are now routinely used in iterative pipelines, where each predicted mask is fed back as the next prompt. This pr…
Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks
Nirjhor Datta, Swakkhar Shatabda, M Sohel Rahman
Large pre-trained DNA language models such as DNABERT-2, Nucleotide Transformer, and HyenaDNA have demonstrated strong performance on various genomic benchmarks. However, most appl…
Entropy-Driven Genetic Optimization for Deep-Feature-Guided Low-Light Image Enhancement
Nirjhor Datta, Afroza Akther, M. Sohel Rahman
Image enhancement methods often prioritize pixel level information, overlooking the semantic features. We propose a novel, unsupervised, fuzzy-inspired image enhancement framework…