Hi, I’m Davide Liu

New and updated version of my personal page here: https://www.notion.so/davideliu/Davide-Liu-40592111c4ac4c59bf2592bce20a53c7?pvs=4

Who am I?

Well…There are 2 versions of me:

  • I’m a blogger and I love talking about technical topics in a friendly and conversational way. I want you to enjoy the process of learning as I do.
  • I’m a data scientist and what I do is feed hungry machine learning models with tons of data. I hope they can learn better than I do.

Short biography

Davide Liu completed his Bachelor’s in Computer Science in Italy at the University of Padova in 2019 and obtained his Master’s in Advanced Computing at Tsinghua University in 2021 conducting research in Reinforcement Learning and Security in AI. His goal is to use AI in a safe and smart way to improve the quality of our life. During his studies, he had the opportunity to attend internships in two AI startups: one in Italy where he improved an existing computer vision algorithm that lead to winning a challenge organized by the US Pentagon, and one in China doing research on novel architectures for recommendation systems which lead to four conference publications. Currently, he is working full-time as AI researcher at SenseTime in Beijing. Outside of his professional life, Davide is an online blogger, athlete, and videogames developer.

How to connect with me

Do you want to know more about my crazy adventures? You should check me on

Are willing to grow with me professionally? No problem, let’s connect other on

Did you find reading my posts useful? Stay updated for the next ones on

And finally, don’t forget to subscribe here to receive information about the latest posts

Do you want to have chat with me?

Academic experiences

2016-2019 Bachelor’s degree in Computer Science at Padova University in Italy.

  • In 2018 I was among the 30 students selected to take part in a cybersecurity and CTF challenge national training program called Cyberchallenge led locally by the Spritz (Security & Privacy Research) group under the supervision of prof. Mauro Conti.
  • In 2019 I joined the VIMP (Visual Intelligence and Machine Perception) group and conducted my thesis research on object tracking and detection under the supervision of prof. Lamberto Ballan. My work was done while in an internship for the startup Studiomapp supported by its founder Leonardo Dal Zovo.

2019-2021 Master’s degree in Computer Science at Tsinghua University in China.

  • In 2020 I joined the TSAIL (Tsinghua Statistical Artificial Intelligence & Learning) group where conducted my thesis research on the robustness of reinforcement learning algorithms against adversarial policies under the supervision of prof. Jun Zhu.
  • Would you like to repeat my experience? This post may be interesting for you

Professional experiences

2021-Present – SenseTime, China, Beijing – AI Policy Researcher

Researcher at OpenDIlLab. Main developer of DI-engine and its ecosystem: a generalized, distributed, and scalable decision intelligence engine that supports various deep reinforcement learning algorithms.

Research, development, optimization, analysis, benchmark, and documentation of several deep reinforcement learning algorithms.

Optimization and analysis of quantitative trading policies with Reinforcement learning, Machine learning, and Genetic algorithms.

2021-Present – Genify, China, Beijing – Tech Lead

First-author papers published at SIGIR’21, IJCCN’22 (Oral), and ICAIF’22 (Oral), ECG’23 leading research on recommender systems.

2020-2021 – Genify, China, Beijing – Data scientist

Designed and implemented a self-attention-based banking products recommendation system performing better than state-of-the-art benchmarks.

Early development of the platform EZ-loan used to estimate the credit score of unbanked customers and API to cluster users according to their financial transactions with ML.

First place at BSF Hackathon by Banque Saudi Fransi and First place at MINT Hackathon by EGbank.

2019-2019 – Studiomapp, Italy, Ravenna – AI Computer vision researcher

Developed an algorithm to enhance the metrics result obtained performing object detection on high-resolution satellite images from the xView dataset.

Developed and tested an algorithm to detect and track specific objects on videos exploiting Faster-RCNN and Kalman filter.

Conference publications

You can also find the following information on Google Scholar and Researchgate.

2021

  • SIGIR ’21 – Transformer-based Banking Products Recommender System (link) – Virtual Event, Canada

2022

  • IJCNN ’22 – BRec the Bank: Context-aware Self-attentive Encoder for Banking Products Recommendation (link) – Oral presentation – Italy, Padova
  • ICAIF ’22 – Sequential Banking Products Recommendation and User Profiling in One Go (link) – Oral presentation – US, New York

2023

  • ECG ’23 – BRec the Bank : encodeur auto-attentif sensible au contexte pour la recommandation de produits bancaires (link) – France, Lyon