Hello World 👋! I'm a software engineer and student researcher at Texas State University. Since starting my journey in 2020, I've built impactful projects across web development, AI, machine learning, and data science. Skilled in TypeScript, JavaScript, Python, React, Next.js, and more, I focus on shipping products that matter. I believe in the mantra: “Do what you want, not what you can!”
Bhanai is a simple and intuitive programming language with a Nepali touch. It leverages Node.js under the hood for execution, allowing users to create `.bhn` files and run them seamlessly.
CognitiveSky is an open-source research infrastructure for analyzing mental health narratives on Bluesky, combining real-time ingestion, NLP pipelines, and an interactive Next.js dashboard. Accepted for presentation at HICSS 2026. The paper will be made after the presentation at the conference.
ComputeNepal is an independent blog and project hub featuring 200+ articles and open-source learning tools covering programming, AI, data science, and web development. Built to make technical education accessible for learners in Nepal and beyond.
CrashTransformer uses transformer models to convert long police crash narratives into concise, causality-focused summaries that help safety analysts and policymakers act faster. Paper submitted to different venues, will be made available shortly after acceptance.
October 2024 - Present
Undergraduate Research Assistant
AIT Lab - TXST, San Marcos, TX
Created 25+ analytical/visualization tools (internal and open-source), processed 150k+ mobility/crash records, and accelerated AI-in-transportation workflows with reproducible pipelines, faculty dashboards, and standardized outputs. Authored or co-authored 5+ manuscripts published or online, with additional submissions (10+) in the pipeline; contributed methods, analysis, modeling, quality control, and documentation across Python, R, and JavaScript. Designed, implemented, and maintain the AIT Lab website in Next.js/Tailwind; 90+ Lighthouse SEO and performance scores; deployed on Vercel with publications, projects, team, and resources sections.
Expected Graduation: May 2028
Bachelor of Science in Computer Science
Texas State University, San Marcos
I am currently pursuing a Bachelor of Science in Computer Science at Texas State University, where I am learning and gaining hands-on experience in various aspects of computer science, in software development, data structures, algorithms, and web technologies.
August 26, 2025 | arXiv preprint arXiv:2508.19239
Model Context Protocols in Adaptive Transport Systems: A Survey
Gaurab Chhetri, Shriyank Somvanshi, Md Monzurul Islam, Shamyo Brotee, Mahmuda Sultana Mimi, Dipti Koirala, Biplov Pandey, Subasish Das
The rapid expansion of interconnected devices, autonomous systems, and AI applications has created severe fragmentation in adaptive transport systems, where diverse protocols and context sources remain isolated. This survey provides the first systematic investigation of the Model Context Protocol (MCP) as a unifying paradigm, highlighting its ability to bridge protocol-level adaptation with context-aware decision making. Analyzing established literature, we show that existing efforts have implicitly converged toward MCP-like architectures, signaling a natural evolution from fragmented solutions to standardized integration frameworks. We propose a five-category taxonomy covering adaptive mechanisms, context-aware frameworks, unification models, integration strategies, and MCP-enabled architectures. Our findings reveal three key insights: traditional transport protocols have reached the limits of isolated adaptation, MCP's client-server and JSON-RPC structure enables semantic interoperability, and AI-driven transport demands integration paradigms uniquely suited to MCP. Finally, we present a research roadmap positioning MCP as a foundation for next-generation adaptive, context-aware, and intelligent transport infrastructures.
June 21, 2025 | arXiv preprint arXiv:2506.18927
From Tiny Machine Learning to Tiny Deep Learning: A Survey
Shriyank Somvanshi, Md Monzurul Islam, Gaurab Chhetri, Rohit Chakraborty, Mahmuda Sultana Mimi, Sawgat Ahmed Shuvo, Kazi Sifatul Islam, Syed Aaqib Javed, Sharif Ahmed Rafat, Anandi Dutta, Subasish Das
The rapid growth of edge devices has driven the demand for deploying artificial intelligence (AI) at the edge, giving rise to Tiny Machine Learning (TinyML) and its evolving counterpart, Tiny Deep Learning (TinyDL). While TinyML initially focused on enabling simple inference tasks on microcontrollers, the emergence of TinyDL marks a paradigm shift toward deploying deep learning models on severely resource-constrained hardware. This survey presents a comprehensive overview of the transition from TinyML to TinyDL, encompassing architectural innovations, hardware platforms, model optimization techniques, and software toolchains. We analyze state-of-the-art methods in quantization, pruning, and neural architecture search (NAS), and examine hardware trends from MCUs to dedicated neural accelerators. Furthermore, we categorize software deployment frameworks, compilers, and AutoML tools enabling practical on-device learning. Applications across domains such as computer vision, audio recognition, healthcare, and industrial monitoring are reviewed to illustrate the real-world impact of TinyDL. Finally, we identify emerging directions including neuromorphic computing, federated TinyDL, edge-native foundation models, and domain-specific co-design approaches. This survey aims to serve as a foundational resource for researchers and practitioners, offering a holistic view of the ecosystem and laying the groundwork for future advancements in edge AI.
May 26, 2025 | arXiv preprint arXiv:2506.04238
A Comprehensive Survey on Bio-Inspired Algorithms: Taxonomy, Applications, and Future Directions
Shriyank Somvanshi, Md Monzurul Islam, Syed Aaqib Javed, Gaurab Chhetri, Kazi Sifatul Islam, Tausif Islam Chowdhury, Sazzad Bin Bashar Polock, Anandi Dutta, Subasish Das
Bio-inspired algorithms (BIAs) utilize natural processes such as evolution, swarm behavior, foraging, and plant growth to solve complex, nonlinear, high-dimensional optimization problems. This survey categorizes BIAs into eight groups: evolutionary, swarm intelligence, physics-inspired, ecosystem and plant-based, predator-prey, neural-inspired, human-inspired, and hybrid approaches, and reviews their core principles, strengths, and limitations. We illustrate the usage of these algorithms in machine learning, engineering design, bioinformatics, and intelligent systems, and highlight recent advances in hybridization, parameter tuning, and adaptive strategies. Finally, we identify open challenges such as scalability, convergence, reliability, and interpretability to suggest directions for future research. This work aims to serve as a foundational resource for both researchers and practitioners interested in understanding the current landscape and future directions of bio-inspired computing.
March 22, 2025 | arXiv preprint arXiv:2503.18970
From S4 to Mamba: A Comprehensive Survey on Structured State Space Models
Shriyank Somvanshi, Md Monzurul Islam, Mahmuda Sultana Mimi, Sazzad Bin Bashar Polock, Gaurab Chhetri, Subasish Das
Recent advancements in sequence modeling have led to the emergence of Structured State Space Models (SSMs) as an efficient alternative to Recurrent Neural Networks (RNNs) and Transformers, addressing challenges in long-range dependency modeling and computational efficiency. While RNNs suffer from vanishing gradients and sequential inefficiencies, and Transformers face quadratic complexity, SSMs leverage structured recurrence and state-space representations to achieve superior long-sequence processing with linear or near-linear complexity. This survey provides a comprehensive review of SSMs, tracing their evolution from the foundational S4 model to its successors like Mamba, Simplified Structured State Space Sequence Model (S5), and Jamba, highlighting their improvements in computational efficiency, memory optimization, and inference speed. By comparing SSMs with traditional sequence models across domains such as natural language processing (NLP), speech recognition, vision, and time-series forecasting, we demonstrate their advantages in handling long-range dependencies while reducing computational overhead. Despite their potential, challenges remain in areas such as training optimization, hybrid modeling, and interpretability. This survey serves as a structured guide for researchers and practitioners, detailing the advancements, trade-offs, and future directions of SSM-based architectures in AI and deep learning..