Yeah, this one is a bit out there, but it was super fun. I built an AI that actually understands memes. It looks at the image and the text together using PyTorch, TensorFlow, and GPT 4. I used early and late fusion techniques to combine vision and language, plus Tesseract OCR to grab text from the image itself. The model hits over 95% accuracy on meme classification. It’s not your typical corporate project, but it shows how multimodal AI can understand humor, culture, and context. Definitely one of my favorite experiments.
For more details, please visit: https://arham-nexus.vercel.app/work/memechecker
1
0
90
Smart Farming Advisor — Agentic AI
The Smart Farming Advisor is an end-to-end agentic AI system that empowers the agriculture sector with data-driven crop recommendations and accurate plant disease detection. Utilizing an intelligent agentic routing system for autonomous intent classification, the platform seamlessly integrates computer vision models (ResNet50) and machine learning classifiers (Random Forest). It features a comprehensive RAG pipeline with semantic search for farming Q&A, bridging a Next.js 14 frontend with a Flask REST API backend. This project emphasizes my ability to orchestrate multi-tool AI assistants and deliver high-impact predictive modeling solutions.
VisiHealth AI – Explainable Medical VQA
VisiHealth AI is a multimodal, explainable Medical Visual Question Answering system designed to analyze complex clinical radiology scans. Utilizing PyTorch, ResNet-50, and BioLinkBERT, the platform fuses text and spatial image patches through a real multi-token cross-attention mechanism to provide accurate clinical insights. It builds diagnostic trust through explainable AI by overlaying attention-map heatmaps on original scans and deriving human-readable rationales from a 4,444-triplet medical knowledge graph. Delivered via a scalable Next.js and Flask architecture, it demonstrates my capability in deep learning and healthcare AI integrations