CV
Education
MSc in Machine Learning, University College London, Sep 2024 – Sep 2025 (expected)
- Core modules: Supervised Learning; Computational Statistics & ML Project; Statistical Models & Data Analysis; Applied ML; Advanced Topics in ML; Bayesian Deep Learning; Inverse Problem; Computer Vision; Multi‑agent Model
- GPA: Distinction (expected)
- Dissertation (expected): Machine Learning with Physics
MSci in Physics with Theoretical Physics, Imperial College London, Oct 2020 – Jun 2024
- Highlights: Advanced Classical Physics (83%); General Relativity (78%); Quantum Field Theory (67%); Unification (66%)
- Other core courses: Solid State Physics (70%); Nuclear & Statistical Physics (72%)
- GPA: Upper Second Class (65.9%)
- Dissertation: High‑Dimensional Research on Brane Solutions, Supergravity & String Theory (78.05%)
Undergraduate Preparatory Certificate for Science & Engineering, University College London, Sep 2019 – Jun 2020
- Results: Mathematics 95%; Physics 91%; Academic English 77%
Research experience
Jan 2025 – Apr 2025: Term 2 Projects Summary — University College London
NLP: Retrieval‑Augmented Generation with Knowledge Graphs & Query Optimization for QA
- Integrated domain‑specific knowledge graphs into a RAG pipeline to improve context retrieval
- Implemented graph embeddings and semantic search with FAISS and PyTorch
- Designed multiple query‑construction strategies for hard questions
Applied Deep Learning: Weakly Supervised Image Segmentation
- Built a segmentation model from image‑level labels with improved Class Activation Maps
- Combined supervised and unsupervised learning for segmentation
Sep 2024 – Jan 2025: Term 1 Coursework Summary — University College London
- Bayesian Deep Learning: Bayesian Classifier coursework — Full marks (50% of module)
Probabilistic & Unsupervised Learning — Full marks (50% of module)
- Decrypting messages using Markov Chain Monte Carlo
- EM for binary data clustering
- Supervised Learning: 98% (20% of module)
Jun 2024 – Jul 2024: Computing & ML Competition — ClimSim (LEAP: Atmospheric Physics using AI)
- Team Silver Medal (Rank 23) on Kaggle
- Built a deep learning emulator using 1D U‑Net + Transformer encoder layers for sub‑grid atmospheric processes
- Achieved strong R² on validation/test; improved physical fidelity of simulations
Jul 2023 – Apr 2024: MSci Project — Imperial College London
- Black Holes and Branes in Supergravity
- Derived brane solutions in D=11 and other dimensions; applied GR & supergravity techniques
- Studied spinor fields in higher‑dimensional spacetimes; investigated T‑duality & dimensional reduction
- Distinction in viva and report (78.05%)
Oct 2023 – Dec 2023: Team Project — SHiP Experiment (FPGA), Imperial College London
- Explored FPGA for real‑time data processing & particle ID in SHiP
- Co‑developed presentation pitch and work plan for FPGA‑based solutions
Jan 2023 – Apr 2023: Team Project — LHCb Rare B‑Meson Decay, Imperial College London
- Led the data‑selection subgroup; implemented efficient analysis code
- Designed core components of the fitting function for raw‑data analysis
- Provided theoretical guidance on ML algorithms (e.g., Decision Trees) for data acceptance
Nov 2022 – Dec 2022: Solid State Physics Project — Imperial College London
- Simulated quantum wells using a tight‑binding model in Python; validated with accurate results
- Built a quantum‑well generator with visual outputs; received full marks
Skills
- Programming & ML: Python; data analysis; machine learning; deep learning; reinforcement learning; FAISS; PyTorch
- Projects (selected): LSTM poem generator; handwriting recognition; drowsiness detection; RL Snake game
- Tools: LaTeX; poster design & presentation
- Languages: English (Fluent); Chinese (Native)
Service and leadership
- Led data‑selection subgroup in LHCb team project
- Kaggle LEAP/ClimSim team silver medal (Rank 23)
- Contributed presentation pitch & planning for SHiP FPGA project