Hi! I'm Bohan Yang, a senior at Cornell University, studying Computer Science with minors in Artificial Intelligence and Business.

I'm passionate about leveraging AI to make the world a better place.

Currently, I'm an undergraduate researcher at the Cornell EmPRISE Lab, advised by Prof. Tapomayukh Bhattacharjee. My recent work includes developing an Human-in-the-loop Query System for Modular Robot Policies Failure Recovery, which enables robots to proactively ask for human help when uncertain, and autonomously learn recovery strategies from failed tasks.

Previously, I researched on LLM-Guided Differential Equation Inference from Cornell MAE department and Machine Learning for Concussion Diagnosis from Harvey Mudd College.

I'm a researcher, an entrepreneur, and a coder. If you share the same passion, feel free to reach out!

Bohan Yang
Bohan Yang

Computer Science @ College of Engineering
Cornell University

Publications

Under Submission

  • R. Banerjee, K. Palempalli*, B. Yang*,J. Fang, A. Abdullah, T. Silver, T. Silver, S. Dean, T. Bhattacharjee. A Human-in-the-loop Confidence-Aware Failure Recovery Framework for Modular Robot Policies."

Journal Papers

Preprints

Projects

MathMentorAI

MathMentorAI Preview

AI-powered mathematics tutoring platform that provides personalized learning experiences. Features adaptive difficulty, natural language interface, and comprehensive progress tracking for students of all levels.

Technologies: Python, Machine Learning, NLP, Educational Technology

Pixelate

Pixelate Preview

AI-powered CAD Copilot for engineers, designers, and makers. A revolutionary startup that transforms how professionals interact with CAD software through natural language commands and intelligent automation.

Technologies: AI/ML, CAD Integration, Computer Vision, NLP

Storytelling Assistant

Storytelling Assistant Preview

A powerful AI-powered tool that helps transform technical content into engaging narratives for different audiences. Features multiple output modes (Investor, Conference, General) and a custom ML-based scoring system for quality assessment.

Technologies: Python, RAG, Transformers, Custom ML Models

DXF2CAD

DXF2CAD Preview

A generative AI framework that learns from 2D DXF blueprints to construct editable 3D CAD models in STEP format in seconds.

Technologies: Python, PyTorch, Transformers

CADParser

CADParser Preview

Reimplementation of a transformer-based model that generate parametric construction sequences from 3D CAD models.

Technologies: Python, PyTorch, Transformers, Graph Neural Networks (DGL)

Parallelizing Diffusion Modeling with MPI

Diffusion MPI Preview

A high-performance parallel simulation of 2D diffusion using MPI.

Technologies: C++, MPI, High Performance Computing

Address Matching

Address Matching Preview

An address matching system to ensure the consistency of healthcare provider directories.

Technologies: Python, Pandas, Locality Sensitive Hashing (LSH)

Pokémon Kingdom

Pokemon Kingdom Preview

An interactive turn-based Pokémon battle game.

Technologies: OCaml