Ashish Behal
AI / ML Engineer

Projects

Click on any project to learn more

Project 1
Learning Chess Without Rules: Discrete Diffusion for Chess Position Generation

Trained a Discrete Denoising Diffusion Probabilistic Model (D3PM) on 500,000 chess puzzle positions — with no explicit knowledge of the rules. The model achieves 69.5% valid position generation versus a 16.3% random baseline, and closely matches the training distribution on pawn structure metrics.

Python PyTorch D3PM Discrete Diffusion Transformers Generative AI Research
Learning Chess Without Rules: Discrete Diffusion for Chess Position Generation
Project 2
IBM Agentic AI Hackathon: 2nd Place

Built a multi-agent RAG system using IBM watsonx Orchestrate to help UB Computer Science students navigate coursework, degree requirements, and faculty research — delivering personalized responses across a range of academic queries. Placed 2nd at IBM's Agentic AI Hackathon at UB.

RAG Multi-Agent Systems Foundation Models IBM watsonx.ai Python
IBM Agentic AI Hackathon: 2nd Place
Project 3
"Auto OH" Office Hours App

Office Hours are important for the academic success of many students, but often end up being hectic and inefficient. This project focuses on streamlining the office hours experience for both students and instructors.

PHP React MySQL Figma Full-Stack Development AI-Assisted Development Agile Scrum Methodology Software Engineering Principles
"Auto OH" Office Hours App
LaTeX Snip
LaTeX Snip

A Chrome extension that converts any on-screen math into clean LaTeX in seconds. Drag a box over an equation, and a vision AI returns the LaTeX rendered as a live math preview — ready to copy anywhere.

AI Engineering Chrome Extension JavaScript API Integration OCR
LaTeX Snip
Project 5
Construction in Progress

Building...

Python
Construction in Progress