08/2022: A journal paper "Dependable learning-enabled multiagent systems" is accepted by AI Communications.
07/2022: Lead by Dr. Yi Dong, our paper "Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking" got accepted by IROS'22.
06/2022: Our 1st year PhD student Yi Qi got a paper "A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems" accepted by AISafety'22 co-located with IJCAI’22.
04/2022: It is my privilege to join AAAI2023 and WAISE2022 as a PC member.
03/2022: Organised together with our colleagues from DSTL and Heriot-Watt Uni a Demo Workshop for SOLITUDE. The 3-hours recorded video is avalible here.
09/2021: Our paper on “Embedding and Extraction of Knowledge in Tree Ensemble Classifiers” is accepted by the Springer journal of Machine Learning.
08/2021: Our AISafety’21 paper won the best paper award, while we are working hard on its journal version! Hopefully it will come out soon.
07/2021: A huge congrats to our PhD student Wei Huang (co-supervised by Xiaowei and me) who is the winner of Siemens AI-Dependability-Assessment-Student-Challenge. News on the school website.
06/2021: Our paper “Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles” is accepted at the workshop AISafety’21 co-located with IJCAI’21. Here is the accepted version.
05/2021: A first XAI paper of mine “BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations” is accepted by UAI2021, thanks to the great efforts of my co-authors. BayLIME (the accepted preprint) is a Bayesian modification of LIME that exploits prior knowledge and Bayesian reasoning to improve the consistency in repeated explanations, the robustness to kernel settings and explanation fidelity.
05/2021: Our journal paper “Coverage Guided Testing for Recurrent Neural Networks” (preprint) got accepted by IEEE Tran. on Reliability. Congratulations to our star PhD student Wei Huang and all co-authors!
04/2021: An abstract paper is accepted by DSN2021 – “Detecting Operational Adversarial Examples for Reliable Deep Learning”, here is a preprint version. Hopefully the more exciting parts, results to the research questions articulated, will come soon.
03/2021: Glad that our paper “Conservative Confidence Bounds in Safety, from Generalised Claims of Improvement & Statistical Evidence” is accepted by DSN2021 (48 accepted out of 295 submissions – 16.3%). Great work by my CSR colleagues Kizito and Lorenzo! Here is a preprint version.
02/2021: It is my great pleasure to be part of the UAI2021 this year as a PC member. Looking forward to reviewing exciting papers from the prestigious community.
01/2021: Give a talk at the FOCETA WP3 workshop on behalf of our Liverpool side. The topic is on reliability assessment for Deep Learning software considering evidence of robustness verification and operational testing.
12/2019: Start a new project “COVE: Continual Verification and Assurance of Robotic Systems Under Uncertainty” as a Co-Investigator. Looking forward to working with Dr. Radu Calinescu and Dr. Simos Gerasimou!
11/2019: Our paper “On Reliability Assessment When a Software-based System Is Replaced by a Thought-to-be-Better One” is accepted by Reliability Engineering and System Safety. It is another joint work, during my PhD study, with colleagues from the Centre for Software Reliability (CSR) at City University of London. Here is a preprint version.
09/2019: Our paper “UAS Operators Safety and Reliability Survey: Emerging Technologies Towards the Certification of Autonomous UAS” is accepted by ICSRS2019. Here is the accepted version.
07/2019: Our paper “Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing”, a joint work with colleagues from the Centre for Software Reliability (CSR) at City University of London, is accepted by ISSRE2019 as a Best Paper Nominee. Here is the accepted version.
06/2019: Our paper “Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management”, a joint work with colleagues from the University of Liverpool, is accepted by SEFM2019. Here is the accepted version.
02/2019: Presented our paper “Probabilistic Model Checking of Robots Deployed in Extreme Environments” at the 33rd AAAI Conference on Artificial Intelligence, Honolulu, Hawaii, 2019.
01/2019: As the start of my AAIP Programme Fellowship, I paid a very first visit to Dr. Radu Calinescu’s team at the University of York, which was a great experience.