My primary research goal is to make future software infrastructures: easy-to-use, high-performance and reliable. At present, I am developing PLSE techniques to make ML Systems reliable and efficient.
My undergrad research has been extensively related to high-performance MLSys, including model serving, tensor compilers, distributed training, etc.
🤗 I am open to collaborate! ->
OOPSLA’22Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass MutationIn Proceedings of the ACM on Programming Languages (OOPSLA) 2022
ACMMM’21Fast and Flexible Human Pose Estimation with HyperPoseIn Proceedings of the 29th ACM International Conference on Multimedia 2021
|2022||OSDI & ATC||Artifact Evaluation Committee Member|