Minglu ZHAO
A PhD student at Shimosaka Lab, Tokyo Institute of Technology
email: zhao.minglu.s2[at]gmail.com
LinkedIn: linkedin.com/in/minglu-zhao-0b98811b1
Bio
Self-introduction. I am a phd student at Tokyo Institute of Technology, in the lab of machine intelligence in UbiComp Research, with Prof. Shimosaka. I received master's degree from the Graduate school of Informatics at Tohoku University. I also completed my Bachelor of Mechanical and Aerospace Engineering at Tohoku University while receiving MEXT (Japanese Government) scholarship.
Research contents. Currently, my research focuses on Inverse Reinforcement Learning with Positive and Negative Driving Behavior Data. You can check my publications here.
In addition to research. I attended Prof. Ohzeki's Quantum Annealing workshop for my personal interests. You can refer to this GitHub repository. I also attended several Kaggle data analysis competitions.
(Bio updated Mar. 2023)
News
Jun 2024, oral. Our paper Inverse Reinforcement Learning with Failed Demonstrations towards Stable Driving Behavior Modeling has been orally presented at IV 2024 (top 5%).
Jun 2023, poster. A poster presentation was given at ROBOMECH2023 in Nagoya, JP. [lab's blog in JP] [research project blog in JP]
May 2022, co-author paper. Automated selection of build configuration based on machine learning at the 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Mar 2022, graduation. I graduated from Takizawa-lab at Tohoku University as a master's degree student. [lab's blog]
Dec 2021, paper. The paper Spatiotemporal Anomaly Detection for Large-Scale Sensor Data has been accepted and presented at PAAP 2021. [lab's blog]
2021, program interview. I had an interview as a student in the International Mechanical and Aerospace Engineering Course at Tohoku University. [interview website]
Dec 2020, paper. Paper Failure Prediction in Datacenters Using Unsupervised Multimodal Anomaly Detection has been accepted and presented at IOTDA 2020. [lab's blog]
Nov 2020, co-author paper award. Our paper Improving the Accuracy in SpMV Implementation Selection with Machine Learning has been nominated for the Best Paper Award at LHAM 2020. [lab's blog]