I am a PhD-track MSc student at the University of British Columbia (UBC). My background spans networks, backend engineering, and applied AI, most recently as a GenAI software engineering intern at Planview. I work on world action models (WAMs), focusing on positional embeddings (RoPE variations) and gaussian diffusion optimizations, aiming to improve the robustness of joint video and action generation.

I previously earned a Bachelor of Commerce from Concordia University, then spent two years in marketing at Sid Lee.

Publications

WAM-Mini: A Fully Configurable Causal Environment for Training Local World Action Models
Christopher Tardy, Frank Wood
2nd UBC CSSRC, 2026
[coming soon]

PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI
Yingchen He, Christian D. Weilbach, Martyna E. Wojciechowska, Yuxuan Zhang, Frank Wood (Acknowledgement)
[site] [link]

Research Blog

Projects

Project Elephant

Directed study under Dr. Frank Wood, UBC. Wraps the NICE DCV Web Client SDK for remote classroom and lab sessions, streaming inputs to S3 for scalable AI training data capture.

Gitopia

A 2D adventure game that teaches Git basics.

Winner, BCS Hacks 2025

Talks

ETA, Casually Explained
CPSC 532X: Test Time Adaptation + Adaptive Computation, UBC (Evan Shelhamer), October 2026
Paper: Efficient Test-Time Model Adaptation without Forgetting, Shuaicheng Niu et al., 2022
[slides]

Training on test data isn’t cheating
PLAI reading group, September 2026
Paper: Test-Time Training with Self-Supervision for Generalization under Distribution Shifts, Yu Sun et al., 2019
[slides]

Awards

Mitacs Accelerate Fellowship, Layer 6 (TD Bank), 2026
Science Undergraduate Research Experience (SURE) Award, UBC, 2026
AML-TN Undergraduate Research Award (NSERC CREATE), 2026
Patrick Prefontaine Scholarship in International Business, 2022