Projects

Real-time AI fact-checker built in 24h for the Anthropic × IIT Madras CBC Hackathon. Streams live verdicts as users type via SSE: Claude Haiku for fast triage, Claude Sonnet for deep analysis. Won 1st Runner Up.

Research-paper intelligence system: ask questions, get citation-grounded answers from your paper library. Semantic search with Qdrant, async ingestion via FastAPI, Claude API for synthesis. Actively in development.

6-model ensemble (including an Audio Spectrogram Transformer) for multi-label music-genre classification. Hit 0.9614 Macro F1, reaching top 2.5% on the leaderboard. AST + SWA soups under tight compute constraints.

RRDBNet built from scratch for the NPPE2 Plant-Leaves Super-Resolution challenge. 11-model ensemble with SWA model soups. Private leaderboard: score 16.569, rank 12 of 866 teams.

Deadline-tracking app for IIT Madras BS students. 9 stars, actively used. Aggregates assignment deadlines, exam dates, and course schedules into a single clean dashboard built in TypeScript.