4 citations · 7 across the 13 of their papers we have counts for
13 papers
HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question Answering
Md Motaleb Hossen Manik, Ge Wang
Biomedical question answering with large language models is commonly evaluated using answer accuracy, but answer accuracy alone does not indicate whether a model can produce parsea…
CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora
Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang
Generative text-to-video systems can produce visually fluent educational clips, but they rarely encode the pedagogical content knowledge (PCK) needed for effective instruction, inc…
ADAPT: AI-Driven Decentralized Adaptive Publishing Testbed
Md Motaleb Hossen Manik, Ge Wang
Scholarly publishing faces increasingly strong stressors, including submission overload, reviewer fatigue, inconsistent evaluation, governance opacity, and vulnerability to manipul…
Unified Deployment-Aware Evaluation of Open Reasoning Language Models
Md Motaleb Hossen Manik, Ge Wang
Open reasoning language models are often compared under mixed sample sizes, partially standardized prompts, and accuracy-centered summaries, which makes practical model selection d…
Emergent decentralized regulation in a purely synthetic society
Md Motaleb Hossen Manik, Ge Wang
As autonomous AI agents increasingly inhabit online environments and extensively interact, a key question is whether synthetic collectives exhibit self-regulated social dynamics wi…
OpenClaw Agents on Moltbook: Risky Instruction Sharing and Norm Enforcement in an Agent-Only Social Network
Md Motaleb Hossen Manik, Ge Wang
Agentic AI systems increasingly operate in shared social environments where they exchange information, instructions, and behavioral cues. However, little empirical evidence exists…
SlideChain: Semantic Provenance for Lecture Understanding via Blockchain Registration
Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang
Modern vision--language models (VLMs) are increasingly used to interpret and generate educational content, yet their semantic outputs remain challenging to verify, reproduce, and a…
ALIVE: An Avatar-Lecture Interactive Video Engine with Content-Aware Retrieval for Real-Time Interaction
Md Zabirul Islam, Md Motaleb Hossen Manik, Ge Wang
Traditional lecture videos offer flexibility but lack mechanisms for real-time clarification, forcing learners to search externally when confusion arises. Recent advances in large…
N-ReLU: Zero-Mean Stochastic Extension of ReLU
Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang
Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive…
ChatGPT vs. DeepSeek: A Comparative Study on AI-Based Code Generation
Md Motaleb Hossen Manik
Background: AI-powered code generation, fueled by Large Language Models (LLMs), is revolutionizing software development. Models like OpenAI's Codex and GPT-4, alongside DeepSeek, l…
Question-Answering System for Bangla: Fine-tuning BERT-Bangla for a Closed Domain
Subal Chandra Roy, Md Motaleb Hossen Manik
Question-answering systems for Bengali have seen limited development, particularly in domain-specific applications. Leveraging advancements in natural language processing, this pap…
Analyzing the Dynamics of COVID-19 Lockdown Success: Insights from Regional Data and Public Health Measures
Md. Motaleb Hossen Manik, Md. Ahsan Habib, Md. Zabirul Islam +2
The COVID-19 pandemic caused by the coronavirus had a significant effect on social, economic, and health systems globally. The virus emerged in Wuhan, China, and spread worldwide r…
A technique to avoid Blockchain Denial of Service (BDoS) and Selfish Mining Attack
Md. Ahsan Habib, Md. Motaleb Hossen Manik
Blockchain denial of service (BDoS) and selfish mining are the two most crucial attacks on blockchain technology. A classical DoS attack targets the computer network to limit, rest…