I am a 4th year PhD student with The Cake Lab @ Wπ. My research focuses on improving deep learning inference for mobile devices without model retraining by leveraging cloud resources and making smart runtime decisions. Please see my publications for more details.
Previously I was with GLOBALFOUNDRIES (previously IBM) as part of their ASIC Product Engineering team in Williston, VT. Please see my work history for more details.
- MODI: Mobile Deep Inference Made Efficient by Edge Computing
- CloudCoaster: Transient-aware Bursty Datacenter Workload Scheduling
- ModiPick: SLA-aware Accuracy Optimization For Mobile Deep Inference
- Characterizing the Deep Neural Networks Inference Performance of Mobile Applications
- MDInference: Balancing inference accuracy and latency for mobile applications
- PieSlicer: Dynamically Improving Response Time for Cloud-based CNN Inference