[2:15]
AccMPEG: Optimizing Video Encoding for Accurate Video Analytics
[2:33]
HALOS: Hashing Large Output Space for Cheap Inference
[2:51]
Learning Compressed Embeddings for On-Device Inference
[3:09]
Collapsible Linear Blocks for Super-Efficient Super Resolution
[3:27]
Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance
[3:45]
URSABench: A System for Comprehensive Benchmarking of Bayesian Deep Neural Network Models and Inference methods