60 citations · 69 across the 11 of their papers we have counts for
11 papers
Compressing Long Context into Answer-Aligned Memory Embeddings for LLM Inference
Md Mostafizer Rahman, Md Faizul Ibne Amin, Md Shahajada Mia +2
Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latency, energy consumption, and G…
Revision-Aware Success Prediction from Multi-Attempt Programming Trajectories
Md Faizul Ibne Amin, Yutaka Watanobe, Daniel M. Muepu +4
Programming outcome prediction plays a central role in data-driven programming education, supporting learner modeling, timely intervention, and adaptive assistance. Yet predicting…
LLM-as-a-Judge for Contest-Style Human-AI Co-Creation: A Reliability-Aware Evaluation Framework for Coding
Md Faizul Ibne Amin, Yutaka Watanobe, Daniel M. Muepu +3
Large language models now judge open-ended outputs and co-create code with programmers, yet judgments of human-AI co-creation must be reliable, comparable across models, and interp…
CodeT5-RNN: Reinforcing Contextual Embeddings for Enhanced Code Comprehension
Md Mostafizer Rahman, Ariful Islam Shiplu, Yutaka Watanobe +3
Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highl…
Error Understanding in Program Code: A Systematic Study of LLM-DL Combinations for Multi-label Classification
Md Faizul Ibne Amin, Yutaka Watanobe, Md. Mostafizer Rahman +2
Programming is a core skill in CS and SE, yet identifying and resolving code errors remains challenging for practitioners. LLMs have shown remarkable capabilities in NL understandi…
Large Language Models for Education and Research: An Empirical and User Survey-based Analysis
Md Mostafizer Rahman, Ariful Islam Shiplu, Md Faizul Ibne Amin +2
Pretrained Large Language Models (LLMs) have achieved remarkable success across diverse domains, with education and research emerging as particularly impactful areas. Among current…
Code Refactoring with LLM: A Comprehensive Evaluation With Few-Shot Settings
Md. Raihan Tapader, Md. Mostafizer Rahman, Ariful Islam Shiplu +2
In today's world, the focus of programmers has shifted from writing complex, error-prone code to prioritizing simple, clear, efficient, and sustainable code that makes programs eas…
Identifying multi-omics interactions for lung cancer drug targets discovery using Kernel Machine Regression
Md. Imtyaz Ahmed, Md. Delwar Hossain, Md Mostafizer Rahman +4
Cancer exhibits diverse and complex phenotypes driven by multifaceted molecular interactions. Recent biomedical research has emphasized the comprehensive study of such diseases by…
RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis
Md. Mostafizer Rahman, Ariful Islam Shiplu, Yutaka Watanobe +1
Effectively analyzing the comments to uncover latent intentions holds immense value in making strategic decisions across various domains. However, several challenges hinder the pro…
Program Repair with Minimal Edits Using CodeT5
Atsushi Shirafuji, Md. Mostafizer Rahman, Md Faizul Ibne Amin +1
Programmers often struggle to identify and fix bugs in their programs. In recent years, many language models (LMs) have been proposed to fix erroneous programs and support error re…
Exploring Automated Code Evaluation Systems and Resources for Code Analysis: A Comprehensive Survey
Md. Mostafizer Rahman, Yutaka Watanobe, Atsushi Shirafuji +1
The automated code evaluation system (AES) is mainly designed to reliably assess user-submitted code. Due to their extensive range of applications and the accumulation of valuable…