Brian Shu

M.S. Computer Science, Purdue · CoRAL Lab

Robot learning for long-horizon manipulation.

I'm Brian Shu. I build the pieces robot learning runs on: simulated tasks and benchmarks, expert demonstrations, and the imitation-learning policies trained on them. I work with Prof. Ahmed H. Qureshi in the Cognitive Robot Autonomy & Learning Lab at Purdue.

Looking for a Summer 2027 research internship · available May 10 – Aug 20, 2027

Projects

  1. Fiatlux

    2026

    A long-horizon benchmark in which a simulated Unitree G1 humanoid climbs a ladder and replaces a light bulb, built in NVIDIA Isaac Lab.

    • Isaac Lab
    • Unitree G1
    • Benchmark
    • USD assets

  2. Dishwasher loading

    2026

    A general dishwasher-loading manipulation policy in NVIDIA Isaac Lab, built on simulated dish assets I released publicly.

    • Isaac Lab
    • Manipulation
    • Planning
    • Imitation learning

  3. Cable insertion

    2026

    A force-monitored expert policy and an imitation-learning pipeline for cable insertion on a UR5, built for the AI for Industry Challenge.

    • ROS 2
    • Gazebo
    • LeRobot
    • ACT
    • Diffusion Policy

  4. DCVLR

    2025

    Data Curation for Visual-Language Reasoning, a pipeline that generates synthetic multimodal question-answer pairs with reasoning steps and uses them to fine-tune Qwen2.5-VL.

    • VLM
    • Synthetic data
    • Qwen2.5-VL
    • Fine-tuning

More work

  • Hyundai CardData Science Intern · Seoul · 2025

    RAG pipeline for text-to-SQL with self-consistency decoding; migrated to an open-source model while keeping 80% execution accuracy.

  • Software verification, UH MānoaSoftware Verification Developer · 2024–2025

    Isabelle/HOL proofs of functional correctness, following the seL4 and RT-11 verification efforts.

  • Biological reaction simulation, UH MānoaResearch Assistant · 2023

    Efficient simulation of a biological reaction model, with 2D and 3D visualization of the results.

  • Jane Street Real-Time Market Data ForecastingKaggle

    Supervised autoencoder + MLP; ranked 440 of 3,000 (top 15%).

  • Spinner Dolphin Photo Grading ProtocolComputer vision

    Multi-stage model that detects, rates and classifies spinner dolphins by fin distinctiveness.

  • BirdCLEF 2024Audio classification

    Transfer-learned MobileNet-v2 on spectrograms to identify under-studied Indian bird species.

  • Higgs Boson DetectionClassification

    Compared scikit-learn classifiers; 11th of 52 on the public leaderboard.

  • OpenAI CarRacingTensorFlow

    2D CNN driving agent in TensorFlow for randomly generated tracks.

  • Full Cycle TakeOutHACC 2023 finalist

    MERN and Meteor web app for ZeroWaste Oʻahu.

  • Protein foldingAlgorithms

    Hydrophobic-polar lattice model solved by recursive backtracking.

  • PANDA programming clubLecturer & Curriculum Developer · 2022–2025

    Designed an algorithms curriculum and led small-group sessions; 2023 Best Officer award.

  • ACM at MānoaServer Administrator & Webmaster · 2023–2024

    Maintained the chapter website and built internal tools for the leadership team.

About

Before Purdue I studied computer science and finance at the University of Hawaiʻi at Mānoa (B.S. and B.B.A., 2026), where I helped build the Fiatlux benchmark with Prof. Igor Molybog. Earlier I interned in data science at Hyundai Card in Seoul and wrote Isabelle/HOL proofs as a software verification developer.

More about me

Contact