Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines.
Published in VLDB, 2024
This paper is about efficient ML serving system and approximate query processing.
Recommended citation: https://arxiv.org/abs/2405.11191
Published in VLDB, 2024
This paper is about efficient ML serving system and approximate query processing.
Recommended citation: https://arxiv.org/abs/2405.11191
Published in NetAI, 2020
This paper is about distributed training of DNN models.
Recommended citation: https://arxiv.org/pdf/2006.10103