LLM Training Teaching Gemma-3 to Reason SFT + GRPO fine-tuning pipeline that improves reasoning in Gemma-3. DarkGuardRL Self-play reinforcement learning for dark pattern detection with Qwen3-4B. Tiny Stories Diffusion Language Model A diffusion language model built from scratch to tell tiny stories. Agentic AI Dynamic Model Router for Tau Runtime LLM routing engine for the Tau coding agent. Secure Multi-Tenant RAG System Enterprise RAG pipeline with role-based access control. Voice-Powered Multimodal RAG Agent Agentic RAG with LangGraph and NVIDIA Nemotron for voice-driven multimodal retrieval. Agent Derma Doc Chatbot Multimodal multi-agent skin disease chatbot. Whiteboard to Workflow Sprint Master Project for Google DeepMind - Vibe code with Gemini 3 on AI Studio on Kaggle. Machine Learning LLM-Augmented GNN for Fraud Detection Combining a fine-tuned SLM with a Skip-GNN for graph fraud detection. Smart Product Pricing Ensemble Model Our solution for Amazon ML Challenge 2025 that ranked 52 out of 9,000+ teams. Multi-View Multi-Objective Extractive Summarizer Unsupervised techniques for extractive document and text summarization.
