Skip to content

AI Projects by Punya Mittal

Research builds, hackathon winners, open-source systems, and product experiments across AI, full-stack, and social impact.

ResearchHackathonsBlockchain ProjectsCloud SecurityMachine Learning

REHAB

2026

REHAB (सीखो और बढ़ो) tackles engagement gaps in rehab programs for underaged children. Piloted at SPYM Rehabilitation Centre, Daryaganj under MY Bharat. Emotion feedback shifted from Confused → Happy; verified by the centre and supported by the District Youth Officer, Central Delhi.

  • EdTech
  • Voice UI
  • Emotion AI
  • Hindi-first

AUTO ML PIPELINE

2026

Context-aware problem canonicalization, multi-gate ethics/feasibility checks, semantic dataset discovery, AutoML (RF / LightGBM / XGBoost), and automated code generation. Evaluated on 33 problems: Acc/R² 0.690, F1 0.746, ~5 min E2E, 85% unsafe-task filtering. Research paper in prep with Garv Bansal & Vaibhav Raj.

  • LLMs
  • AutoML
  • Python
  • Responsible AI

GEAR LAB PRO

2026

Constrained multi-objective gear-ratio optimization with traction limits, event simulation (Accel / Skidpad / Autocross), voice commands, offline fallback, mobile trackside UI, and RPM-driven engine sound synthesis. A digital race engineer for FS teams.

  • React
  • Optimization
  • AI
  • Motorsport

HOSPITAL RAG

2026

Worked with hospital IT on digital pen / dot-paper digitization of handwritten records, vendor workflows, and AI/ML training for handwriting. Built a RAG chatbot over hospital docs and researched private open-source LLM deployment for healthcare privacy.

  • RAG
  • LLMs
  • Healthcare IT
  • Knowledge Base

KAI

2025

Kai simulates emotions, long-term memory, personality, and regulation — designed to feel less like a chatbot and more like a digital personality. Explores human-centric applied AI research.

  • LLMs
  • Python
  • Memory Systems
  • Ethics

LLM GUARD

2025

Defense-in-depth: ML detector on 100k+ prompts, rule filters, benign whitelisting, confidence escalation. ~99–100% recall, <2% FN, >50% FP reduction. Hybrid verdict engine for agent/tool safety.

  • ML
  • LLM Security
  • Python
  • Cybersecurity

CRISPROOTS

2025

Redesigning Indian agriculture with AI-powered precision: gene-editing insights + real-time digital twin ecosystems for sustainable farming. Built for ANNAM.AI Hackathon 2025 (4th place) at IIT Ropar — CoE of the Ministry of Education.

  • AgriTech
  • AI
  • Digital Twins
  • Sustainability

FATED.CHAT

2025

Campus-closed network where matches come from structured compatibility forms, not photo-first swipes. Experiment in engineering meaningful connections for university students.

  • Full Stack
  • Matching
  • Campus Product

Y-SOC

2025

Founded Y-SoC to help students go from idea → impact. 1000+ entries, top 20% selected, 60+ GitHub projects, workshops, hackathons, and partnerships (incl. GEMINATHON '26 with Google Gemini). Motto: You Code. You Create. You Collaborate.

  • Open Source
  • Community
  • Leadership

Also explore AI work, research, and blockchain projects.