Robotics · Embodied AI · Edge ML
Hi, I'm Wenjin Fu
Machine Learning Engineer at OpenMind · San Francisco
I build perception and learning systems that help robots understand the space around them and act reliably on real hardware. Before OpenMind I worked on image analysis at Apple. I hold an M.S. in ECE from Carnegie Mellon and a B.S. in CSE from Ohio State. More about me →
Open-vocabulary 3D mapping Sensor fusion On-device LLMs Human–robot interaction
🤖 Building robots that see
📍 San Francisco
What I work on
Research interests
Robot Perception
Detection, recognition and sensor fusion that run on real robots, from data strategy to fleet deployment.
Spatial Intelligence
Open-vocabulary 3D maps: knowing what each object is, where it is, and whether it will still be there tomorrow.
Efficient On-Device AI
Compressing and adapting LLMs and vision models to meet latency, memory and energy budgets on the edge.
Research
All publications → Selected publications
ECCV 2022 NeurIPS 2025 Workshop Electronic Imaging 2026
Learning with Free Object Segments for Long-Tailed Instance Segmentation
C. Zhang, T.Y. Pan, T. Chen, J. Zhong, Wenjin Fu, W.L. Chao
CAFL-L: Constraint-Aware Federated Learning with Lagrangian Dual Optimization for On-Device Language Models
Dongqi Zheng, Wenjin Fu
A Real-Time On-Device Defect Detection Framework for Laser Power-Meter Sensors via Unsupervised Learning
Dongqi Zheng, Wenjin Fu, Guangzong Chen
Journey
Full timeline → Experience
- 2025 – nowOpenMindMachine Learning Engineer · Robotics
- 2025AppleMachine Learning Engineer
- 2024Coherent Corp.AI/ML Industry 4.0 Intern
- 2023 – 2024Carnegie Mellon UniversityM.S. Electrical & Computer Engineering