M.Tech CSE  ·  SSN College of Engineering, Chennai

Nikhil Karthik S

ML Researcher Full-Stack Dev Systems Engineer

Building intelligent systems at the intersection of Machine Learning, NLP, and Software Engineering.

Repos
2 Publications
3rd MediaEval '25
T10 ACL '26
scroll
01

About

I'm a 3rd-year M.Tech (Integrated) CSE student at SSN College of Engineering. I work across the full stack — from systems-level networking tools and IoT hardware to fine-tuned language models and deep learning pipelines.

My research has been recognised at MediaEval 2025 (3rd place, GI Imaging VQA) and DravidianLangTech 2026 at ACL (Top 10, Tamil NLP). I'm preparing for internships and further publications.

I'm drawn to hard problems — routing anomalies, pixel-level change detection, abusive language in low-resource languages. I care about getting the details right.

Machine Learning
🧠NLP & LLMs
👁Computer Vision
🌐Systems & Networks
📡IoT & Embedded
📐Algorithms
Core Coursework
DSAOSNetworks MLImage ProcessingDBMS Prob & StatsLinear Algebra
02

Education

Aug 2023 — Apr 2028 Current

M.Tech (Integrated) Computer Science & Engineering

Sri Sivasubramaniya Nadar College of Engineering, Chennai
8.532CGPA till 5th semester
Jan — Sept 2024 Online

Foundation Course on Programming & Data Science

Indian Institute of Technology Madras  ·  Online BS Degree
Jun 2008 — Apr 2023 Pre-KG → Class XII

Srivi Lions Matriculation Higher Secondary School, Srivilliputtur

Computer Science & Mathematics Stream  ·  Classes XI–XII
570/600 Class XII
559/600 Class XI
460/500 Class X

† School-level assessment only — AY 2020–21 Class X students were declared all-pass; no government board exam was conducted.

03

Research & Publications

🥉 3rd

BLIP-2 VQA with Multimodal Explanations for Gastrointestinal Imaging

MediaEval 2025 — Subtask 2  ·  CEUR Workshop Proceedings

Applied BLIP-2 to the Kvasir-VQA-x1 dataset for VQA on endoscopy images, generating answers with explanations, attention maps, and confidence scores. Achieved 3rd place internationally.

BLIP-2Medical VQAVision-LanguagePublished
Top 10

IndicBERT for Abusive Tamil Comment Classification

DravidianLangTech 2026 — ACL Workshop  ·  Draft Prepared

Fine-tuned IndicBERT for Tamil abusive language detection with class weighting and threshold optimisation. Achieved Macro F1 of 0.8001, ranking in the top 10 of the shared task.

IndicBERTTamil NLPLow-ResourceACL 2026
~3.99

Hull Tactical Market Prediction — Kaggle

Kaggle Competition  ·  ML & Quantitative Finance

ElasticNet model with feature engineering, EWM imputation, and 10-fold cross-validation. Trading signals optimised by Sharpe ratio — final score ~3.99.

ElasticNetTime SeriesFeature EngineeringFinance
04

Projects

CLI Tool

plagcheck — PDF Plagiarism Detector

CLI tool comparing two PDF assignments across text (cosine, Jaccard, Dice n-grams), code (AST-level Python normalisation), visuals (perceptual hashing + tile matching), and document structure. Three-stage extraction pipeline; runs fully offline.

PythonASTpdfplumberPyMuPDFOCRPerceptual Hash
Ongoing

Real-Time Accident Detection System

IoT crash-detection using Raspberry Pi, sensors, GPS, and GSM. Dispatches emergency alerts on collision with SOS button and environmental monitoring. IFSP collaboration.

Raspberry PiPythonGPS/GSMIoT
LLM

Legal Assistant: Police Station Management

Full-stack legal platform with a Mistral chatbot fine-tuned on Indian law data. Graph-native Neo4j backend for relationship-aware queries. Django API + Next.js frontend.

DjangoNext.jsNeo4jMistralHuggingFace
Hackathon Finalist

QR Guard — Malicious QR Detection

Scans QR codes, extracts and traces URLs, and classifies threats as safe/suspicious/malicious using heuristic rules and a trained ML classifier.

PythonMLURL AnalysisHeuristics
Full-Stack

Lost & Found Website

Platform for reporting and reclaiming lost items with auth, image-based posting, and a claim workflow. Vue.js frontend with Spring Boot REST API and MongoDB.

Vue.jsSpring BootMongoDB
Networks

Silent Loop Detector

Detects routing loops via TTL variation and packet timing analysis. Real-time Flask dashboard with configurable alerts and anomaly visualisation.

PythonScapyFlaskNetworking
Deep Learning

Change Detection using U-Net

Segmentation model on the Inria aerial dataset with CLAHE preprocessing. Generates pixel-level change detection maps from before/after imagery.

PyTorchU-NetCUDACV
Django

Engineering Seat Allocator

Automated seat allocation with student preference handling and matrix-based logic. Deployed on PythonAnywhere using SQLite; PostgreSQL locally.

DjangoPostgreSQLSQLitePythonAnywhere
Research

Optimisation Algorithm Evaluation

Compared SGD, Momentum, Adam, RMSProp, Adagrad, Adadelta, LBFGS, and Photon on Rosenbrock, Rastrigin, Ackley, and Himmelblau benchmarks. Adaptive optimisers proved most stable.

PyTorchCUDAOptimisationBenchmarking
05

Skills

{ }

Languages

PythonC++JavaCJavaScript

Frontend

HTML/CSSVue.jsNext.js

Backend

DjangoSpring BootFlask

Databases

PostgreSQLMySQLSQLiteMongoDBNeo4jCassandraRedis
🧠

ML / Data

PyTorchscikit-learnNumPyPandasMatplotlibSeaborn

Big Data & Tools

HadoopPySparkGitLinuxScapyDocker
06

GitHub

Fetching repositories…
07

Contact

Open to research collaborations, internship opportunities, and conversations about ML, systems, or software engineering.

Best reached by email — I try to respond within a day.