Skip to content
View raipalorange's full-sized avatar
💭
Yearning
💭
Yearning
0 followers · 2 following

Block or report raipalorange

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
raipalorange/README.md

Siddharth Raipal

MS CS @ USC (graduating May 2026). Previously MLE at an early-stage startup in India.

I work on machine learning systems — graph neural networks, retrieval-augmented generation, and applied ML for healthcare.

Research

  • Published in Knowledge-Based Systems (KBS) — Multi-agent glaucoma patient chatbot - "GlaucomaGuide"
  • RESL Lab, USC — Multi Agent RL for robotic learning
  • Info Lab, USC — Interpretable Dementia Risk Precision tool

Projects

  • Graph RAG Nutrition Chatbot — End-to-end Graph RAG pipeline over 30 nutrition papers. Leiden community detection, hybrid retrieval (entity + semantic), Pinecone + Llama3-70B.
  • ICGRNN — Input convex graph recurrent neural networks for heat diffusion control on graphs. Convexity-preserving message passing + temporal updates.

Links

Pinned Loading

  1. graph-rag-nutrition graph-rag-nutrition Public

    Graph RAG pipeline for nutrition Q&A — extracts knowledge graphs from 30 research papers, clusters with Leiden community detection, and retrieves answers via hybrid graph + semantic search.

    Python

  2. ICGRNN ICGRNN Public

    Forked from MichaelSperling1/ICGNN

    Implementation of Input Convex Graph Recurrent Neural Networks with novel heat diffusion applications. Combines convex optimization principles with graph neural networks for guaranteed optimization…

    Jupyter Notebook