Mathematics — University of British Columbia
I'm a Mathematics undergraduate at the University of British Columbia (BSc, expected 2027–2028). My current focus is robotics: I'm working on an independent robotics project with a hardware component and pursuing a research position in the field. I previously worked as a research assistant on transformer-based neural retrieval with Dr. Jian Zhu and on multilingual transformer representation alignment with Dr. Isabel Papadimitriou, both at UBC.
My interests span linear algebra, stochastic processes, optimization, and reinforcement learning, with a growing interest in robotics and quantitative finance: the mathematics of uncertainty, risk, and how rigorous modeling translates into real decisions.
Alongside my technical work, I founded and lead the AWM chapter at UBC, the first undergraduate chapter of the Association for Women in Mathematics at this institution.
Worked on Reason-ModernColBERT and SPLADE within a two-stage neural retrieval pipeline, evaluated on the BRIGHT benchmark. HPC engineering across Sockeye, Fir, Rorqual, and Narval using Apptainer/Singularity and Slurm-managed GPU jobs. Presented a poster and 3-minute thesis at Canadian AI 2026 (Responsible AI Track) on fairness and representational gaps in transformer-based retrieval.
Studied how multilingual transformers (mBERT, XLM-R) represent and align linguistic structure across languages, and what drives cross-lingual generalization, using probing and representational-similarity methods.
2023 – 2027/2028 (expected)
BSc, Mathematics. Coursework in proof-based mathematics, linear algebra, stochastic processes, optimization, numerical methods, and logic. Founding President of the Association for Women in Mathematics (AWM) chapter.
Prior
Competitive physics background: Gold Medal, IBSKC.
Index — Projects
Quantitative, machine learning, reinforcement learning, and NLP projects
JavaScript · VTK.js · ITK-Wasm
A browser-based DICOM/NIfTI viewer for personal MRI and CT exploration: 3D surface rendering alongside synchronized axial, coronal, and sagittal slice views. Everything runs client-side — files are parsed and rendered locally in WebGL, nothing is uploaded to a server.
Python · PyTorch · Finnhub API · yfinance
A research-grade reinforcement learning system that trains a PPO agent to trade a 7-asset portfolio across tech, finance, energy, and ETF markets, combining NLP-driven sentiment analysis with rigorous walk-forward validation, multi-seed testing, and ablation studies to ensure scientific robustness and generalizability.
Python · NumPy · SciPy
A Monte Carlo simulation framework in Python for modeling stochastic asset price dynamics under uncertainty. Asset price paths are generated using Geometric Brownian Motion under risk-neutral measure to estimate the fair value of financial derivatives, with sensitivity analysis across volatility and time-to-maturity parameters.
Python · PyTorch
A tabular Q-learning agent implemented in PyTorch, trained on a Gridworld environment using Bellman optimality equations. The project explores policy learning under varying learning rates, evaluates performance via empirical return distributions, and includes hyperparameter sensitivity analysis.
Python · pandas · HYDAT
A quantitative feasibility study modeling hydroelectric output under stochastic river-flow dynamics using flow-duration curves and HYDAT data. The analysis includes scenario and sensitivity analysis, tail-risk evaluation, and assessment of long-run economic viability.
Python · pandas · NumPy
A cointegration-based pairs trading strategy with rolling z-score entry and exit signals, realistic transaction costs, and out-of-sample evaluation on pairs selected from unseen data — built to test whether the mean-reversion edge survives outside the sample it was found in.
Python · PyTorch
A transformer architecture implemented from scratch in PyTorch, following Vaswani et al. (2017): multi-head self-attention, sinusoidal positional encoding, and layer normalization, built to understand every moving part of the architecture behind modern NLP.
Started the AWM chapter at UBC in January 2026 to build a real community for women studying math at UBC. It has grown into a full executive team spanning communications, events, finance, mentorship, and technology, with backing from the UBC Mathematics Department and PIMS.
Feel free to reach out about research, collaborations, or anything in between.
EEmail