Find the causal component.
Activation intervention and gradient-based sensitivity analysis to pinpoint where a behaviour lives — down to a single cross-attention head and a low-dimensional subspace inside it.
I study how vision–language models represent what they see — and how to control those representations, precisely and verifiably.
Activation intervention and gradient-based sensitivity analysis to pinpoint where a behaviour lives — down to a single cross-attention head and a low-dimensional subspace inside it.
Magnitude-normalized subspace actuation, iterative trust-region controllers, and selective gates that decide when to act — all on frozen models, without retraining.
Paired exact McNemar tests, bootstrap confidence intervals, rank-matched controls, and untouched evaluation cohorts frozen before any result is seen.
Supervised by Associate Researcher Jiaxi Yang. Built AROMA end to end: reproducible Python, PyTorch and Hugging Face pipelines for multimodal inference, activation intervention, gradient-based sensitivity analysis and statistically controlled candidate evaluation.
Enterprise LLM-RAG customer-service platform: domain-aware semantic retrieval, agent–human handoff for ambiguous and long-tail queries, parameter-efficient fine-tuning for local deployment, and multidimensional metrics for conversational quality. Worked across ML, software and DevOps teams to ship GPU-accelerated services in containers.
Reproduced the KTransformers heterogeneous inference framework with DeepSeek-MoE-16B under Q2-K quantization on consumer GPUs; tuned expert offloading and placement and profiled throughput, VRAM and host-memory trade-offs.
Hundsun Technologies
Modular AI service backend with Redis SETNX concurrency control, persistent dialogue state and streaming responses; an end-to-end RAG pipeline over ChromaDB; and QLoRA fine-tuning of Qwen2.5-7B-Instruct on 17,946 dialogues with 4-bit NF4 — containerized with GPU passthrough.
York ABMP Career-Fit Program
Agentic-RAG, multi-agent prototype for identity verification, financial-risk assessment and watch-list screening, with an auditable TCP Double-Lock for high-risk transactions under CIRO / FINTRAC constraints. Mentored by IBM AI SME Utkarsh Pandey; selected as an outstanding participant.
Full-stack web application
Account-driven e-commerce platform covering authentication, cart, checkout, promotions and order processing, with object-oriented domain modelling and validated REST APIs for addresses, coupons, transaction state and insufficient-fund edge cases.
PyTorch · Hugging Face Transformers · NumPy · pandas · scikit-learn · causal intervention · activation steering · statistical testing
LoRA · QLoRA · PEFT · TRL · BitsAndBytes NF4 · MoE inference profiling · GPU inference optimization
ChromaDB · semantic retrieval · retrieval-augmented generation · agentic RAG · multi-agent orchestration
FastAPI · Pydantic · Redis · MySQL · WebSocket · Docker · Python · Java · C · JavaScript · Linux
Bachelor of Computer Science, Computer Science Specialist
Aug 2024 — Expected Jun 2028 · Toronto, Ontario
Interested in mechanistic interpretability, controllable multimodal models, or research collaboration — I’d be glad to hear from you.