ICASSP Presentations

Dr. Zhao presented two papers at the flagship signal processing conference ICASSP and its satellite workshop on “A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning” (YouTube video) and “Confidence-based Federated Distillation for Vision-based Lane-centering”.


Congrats to VISA PhD student Kaiqi Zhao on her paper “Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions” (YouTube Video) published and presented at AISTATS, a top AI conference.

Fighting COVID-19 with federated learning

The spread of the Corona Virus Disease 2019 (COVID-19) has reached pandemic levels across the globe. There is an urgent need to develop CT apps that not only monitor but also intervene to limit COVID-19 spread while respecting user security and privacy. Sponsored by National Science Foundation, this project addresses this challenge via Federated Analytics[…]