View project →Activation-Weighted Low-Rank Compression
Research paper proposing an activation-weighted fitting method that reduces perplexity degradation by 5-7x vs plain SVD across GPT-2, Gemma-3, and Qwen2.5.
Featured Projects
View all projectsView project →
View project →Velora Custom LM Trainer
A from-scratch PyTorch trainer for a compact LLaMA-style language model with resumable training and guided structured generation.
View project →AI Fitness Trainer
A privacy-first, locally-run AI fitness coach combining YOLOv11 pose estimation with a vision-language model for real-time rep counting, form analysis, and AI coaching.
View project →CityBuilder — A Self-Contained Micro-City Simulation with Local AI
A full-stack micro-city MVP with a FastAPI simulation engine, React/TypeScript dashboard, interactive canvas map, and a local Q-learning policy agent — no external AI APIs required.
View project →MagneticStorage — Biologically-Inspired Agentic Memory
A local, biologically-inspired agentic memory system that organizes information into hierarchical concept groups and cells, going beyond flat RAG with three-stage hybrid search, entity routing, and LLM-driven consolidation.
View project →Forest Protector
A Python tower-defense game with 10 escalating waves, 50 dynamic path combinations, tower upgrades, economy, and a live GitHub Pages build.
View project →AI Face Detect and Recognition WebGPU
A client-side AI face tracking and recognition application running YOLOv11 face detection and EdgeFace embeddings directly in the browser via WebGPU and ONNX Runtime.
Skills
Programming Languages
PythonJavaScriptSQLBash
ML Libraries & Frameworks
NumPyPandasScikit-learnTensorFlowPyTorchMatplotlib
Computer Vision
OpenCVImage ProcessingData AugmentationYOLOFace RecognitionObject Detection
Deep Learning
CNNNeural NetworksModel TrainingTransfer LearningFeature Extraction
NLP & Generative AI
LangChainOpenAI APIOllamaText ProcessingQuery DecompositionLLM Integration
Deployment & Tools
REST APIsGitGitHubModel DeploymentGradioWebSockets
Databases
MySQLMongoDBChromaDB
Web Technologies
React.jsNext.jsHTML/CSSTailwind CSS
Development Tools
VS CodePyCharmJupyter NotebookGit
Operating Systems
WindowsLinux
Resume Timeline
Full resumeB.Tech in Computer Science (AI-IBM)
Coursework: machine learning, NLP, time series, statistics, and full-stack development
Club Member, Abhyudaya Coding Club
Built AI timetable-generation work and ran Python, NumPy, Pandas, and Scikit-learn workshops
Independent AI Project Work
Velora transformer training, AI fitness coaching, multi-agent workflows, YOLO face recognition, and simulation systems
Introduction to Machine Learning
NPTEL Online Certification, IIT Kharagpur
Activation-Weighted Low-Rank Compression Research
Published research on transformer weight compression achieving 5-7x improvement over SVD baseline
Hackwave 2.0
36-hour hackathon focused on rapid prototyping, teamwork, and product problem-solving
Writing & Research
View allAug 15, 2026
ReadActivation-Weighted Low-Rank Compression of Transformer Weights
Activation-weighted closed-form low-rank fitting defeats plain SVD by 5-7x in perplexity delta across GPT-2, Gemma-3, and Qwen2.5.
Jun 28, 2026
ReadThree-Stage Hybrid Search with Entity Routing
How to combine centroid search, parallel per-group HNSW queries, and entity routing into a recall-safe hybrid search pipeline.
Jun 26, 2026
ReadSleep Mode: Agentic Memory Consolidation
Designing a consolidation pass that merges similar concept groups using both vector similarity and LLM-based contradiction analysis.