Xiaoyi Zhang
About Me
I am a ML research engineer (9 direct reports) at Apple since 2018, passionate about building user‐friendly developer tools for ML engineers to boost their productivity. My team built ML infra for model analysis, optimization, and testing, which is mission-critical for the launch of Apple Intelligence (Research post, Optimization section) and Vision Pro (Paper).
I received CS (HCI focus) PhD from UW, and interned at Google Research (with Kayur Patel on Colab) and MSR (with Meredith Ringel Morris). My first project at Apple was extending my PhD research to an ML-powered iOS accessibility feature that supports 20M+ blind users’ daily life.
Research Interests: ML Developer Tools, ML Model Optimization, UI Accessibility, HCI.
Achievements:
- Auto-OPT: ML infra to optimize all Apple Intelligence LLMs (on-device & server).
- Talaria: Developer tool to enable Vision Pro ML models to run in low latency.
- Screen Recognition: The first on-device ML model to recognize and announce iOS App UI, benefiting 20M+ blind users.
- 2 Best Papers, 3 Best Paper nominees, 5 Patents.