Speaker:
Mr. ZHOU Dongruo

Abstract:

Reinforcement learning (RL) has achieved great empirical success in many real-world problems in the last few years. However, many RL algorithms are inefficient due to their data-hungry nature. Whether there exists a universal way to improve the efficiency of existing RL algorithms remains an open question.

In this talk, I will give a selective overview of my research, which suggests that efficient (and optimal) RL can be built through the lens of uncertainties. I will show that uncertainties can not only guide RL to make decisions efficiently, but also have the ability to accelerate the learning of the optimal policy over a finite number of data samples collected from the unknown environment. By utilizing the proposed uncertainty-based framework, I design computationally efficient and statistically optimal RL algorithms under various settings, which improve existing baseline algorithms from both theoretical and empirical aspects. At the end of this talk, I will briefly discuss several additional works, and my future research plan for designing next-generation decision making algorithms.

Biography:
ZHOU Dongruo is a final-year PhD student in the Department of Computer Science at UCLA, advised by Prof. Quanquan Gu. His research is broadly on the foundation of machine learning, with a particular focus on reinforcement learning and stochastic optimization. He aims to provide a theoretical understanding of machine learning methods, as well as to develop new machine learning algorithms with better performance. He is a recipient of the UCLA dissertation year fellowship.

Join Zoom Meeting:
https://cuhk.zoom.us/j/93549469461?pwd=R0FOaFdxOG5LS0s2Q1RmaFdNVm4zZz09
Meeting ID: 935 4946 9461
Passcode: 202300

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. Shi QIU

Abstract:

As a fundamental 3D data representation, point clouds can be easily collected using 3D scanners, retaining abundant information for AI-driven applications such as autonomous driving, virtual/augmented reality, and robotics. Given the prominence of deep neural networks in current days, deep learning-based point cloud data understanding is playing an essential role in 3D computer vision research.

In this seminar, we focus on learning deep feature representations of point clouds for 3D data processing and analysis. Basically, we start from investigating low-level vision problems of 3D point clouds, which helps to comprehend and deal with the inherent sparsity, irregularity and unorderedness of this 3D data type. On this front, we introduce a novel transformer-based model that fully utilizes the dependencies between scattered points for high-fidelity point cloud upsampling. Moreover, we deeply explore high-level vision problems of point cloud analysis, including the classification, segmentation and detection tasks. Specifically, we propose to (i) learn more geometric information for accurate point cloud classification, (ii) exploit dense-resolution features to recognize small-scale point clouds, (iii) augment local context for large-scale point cloud analysis, and (iv) refine the basic point feature representations for benefiting various point cloud recognition problems and different baseline models. By conducting comprehensive experiments, ablation studies and visualizations, we quantitatively and qualitatively demonstrate our contributions in the deep learning-based research of 3D point clouds.

In general, this seminar presents a review of deep learning-based 3D point cloud research, introduces our contributions in learning deep feature representations of point cloud data, and proposes research directions for future work. We expect this seminar to inspire further exploration into 3D computer vision and its applications.

Biography:
Shi Qiu is a PhD candidate at Australian National University and a postgraduate researcher at Data61-CSIRO. Previously, he obtained his bachelor degree of Electronic Engineering from Dalian University of Technology in 2015, and master degrees of Digital Media Technology from KTH and UCL in 2017. His main research interests are in 3D computer vision and virtual/augmented reality, where he has authored a few research papers in top venues including T-PAMI, CVPR, etc. In addition to academic research, he also interned at industry-based labs including Vivo AI Lab and Tencent’s XR Vision Labs. He is a recipient of scholarships funded by China, EU, and Australia.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Kazushi Ikeda
Nara Institute of Science and Technology (NAIST)

Abstract:

In this talk, I introduce some studies in Mathematical Informatics Lab, NAIST. Mathematical models are a strong tool in science to describe the nature. However, they are also useful in engineering or even in computation. One example of the math models is the deep learning theory. In deep learning, so many techniques, such as drop-out and skip connections, have been proposed but their effectiveness is not clear. We analyzed it by considering their geometrical meaning.  I show other examples in science and engineering in our projects.

Biography:
Kazushi Ikeda got his B.E., M.E., and Ph.D. in Mathematical Engineering from University of Tokyo in 1989, 1991, and 1994. He joined Kanazawa University as an assistant professor in 1994 and became a junior/senior associate professor of Kyoto University in 1998 and 2003, respectively. He has been a full professor of NAIST since 2008.
He was a research associate of CUHK for two months in 1995.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. MENG Wei
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

Abstract:

The Internet has powered a large variety of important services and applications, such as search, social networking, banking and shopping. Because of their increasing importance, the applications and their huge number of users on the Internet have become the primary targets of cyber attacks and abuses. However, the dynamic nature of the complex modern software makes it very difficult to reason about the security of those applications, especially by using static program analysis techniques.

In this talk, I will share my experience in understanding and improving application security with dynamic program analysis approaches. I will illustrate it with two representative works that address two emerging threats. First, I will introduce how we investigated click interception on the web with a dynamic JavaScript monitoring system. Second, I will present how we combined static analysis and dynamic analysis to accurately detect algorithmic complexity vulnerabilities. Finally, I will discuss about the other challenges and opportunities for further securing software applications.

Biography:
Wei Meng is an Assistant Professor in the Department of Computer Science and Engineering, The Chinese University of Hong Kong.   His main research interests are in computer security and privacy. He designs and builds systems to protect end users and applications on the Internet. His research has been published primarily at top conferences such as IEEE S&P, USENIX Security, CCS, WWW, and ESEC/FSE. He received his Ph.D. degree in Computer Science from the Georgia Institute of Technology in 2017 and his Bachelor’s degree in Computer Science and Technology from Tsinghua University in 2012. He currently leads the CUHK Computer Security Lab in the CSE department.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. YANG Ming-Chang
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

Abstract:
In light of technological advancement over the last few decades, there have been many revolutionary developments in memory and storage technologies. Nevertheless, though these emerging technologies offer us new design choices and trade-offs, deploying them in modern memory and storage systems is non-trivial and challenging. In this talk, I will first summarize our efforts in embracing the cutting-edge technologies in memory and storage systems through co-designing the hardware and software. To make a case, I will present two of our recent studies: one in delivering a scalable, efficient and predictable hashing on the persistent memory (PM) technology and the other in constructing a cost-effective yet high-throughput persistent key-value store on the latest hard disk technology called interlaced magnetic recording (IMR). Finally, I will highlight some new promising memory/storage technologies that may pave new paths for and even completely revolutionize the upcoming computer systems.

Biography:
Ming-Chang Yang is currently an Assistant Professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He received his B.S. degree from the Department of Computer Science at National Chiao-Tung University, Taiwan, in 2010. He received his Master and Ph.D. degrees from the Department of Computer Science and Information Engineering at National Taiwan University, Taiwan, in 2012 and 2016, respectively. He now serves as an Associate Editor in ACM Transactions on Cyber-Physical Systems (TCPS). Also, he served as a TPC co-chair for NVMSA 2021 and as a TPC member for several major conferences. In addition, he received 2 best paper awards from the prestigious conferences in his field (including ACM/IEEE ISLPED 2020 and IEEE NVMSA 2019). His primary research interests include the emerging non-volatile memory and storage technologies, memory and storage systems, and the next-generation memory/storage architecture designs. For details, please refer to his personal homepage: http://www.cse.cuhk.edu.hk/~mcyang/

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. WONG Chi-Wing Raymond
Professor
Department of Computer Science and Engineering
The Hong Kong University of Science and Technology

Abstract:
When faced with a database containing millions of tuples, an end user might be only interested in finding his/her favorite tuple in the database. In this talk, we study how to help an end user to find such a favorite tuple with a few user interations. In each interaction, a user is presented with a small number of tuples (which can be artificial tuples outside the database or true tuples inside the database) and s/he is asked to indicate the tuple s/he favors the most among them.

Different from the previous work which displays artificial tuples to users during the interaction and requires heavy user interactions, we achieve a stronger result. Specifically, we use a concept, called the utility hyperplane, to model the user preference and an effective pruning strategy to locate the favorite tuple for a user in the whole database. Based on these techniques, we developed an interactive system, called FindYourFavorite, and demonstrate that the system could identify the favorite tuple for a user with a few user interactions by always displaying true tuples in the database.

Biography:
Raymond Chi-Wing Wong is a Professor in Computer Science and Engineering (CSE) of The Hong Kong University of Science and Technology (HKUST). He is currently the associate head of Department of Computer Science and Engineering (CSE). He was the associate director of the Data Science & Technology (DSCT) program (from 2019 to 2021), the director of the Risk Management and Business Intelligence (RMBI) program (from 2017 to 2019), the director of the Computer Engineering (CPEG) program (from 2014 to 2016) and the associate director of the Computer Engineering (CPEG) program (from 2012 to 2014). He received the BSc, MPhil and PhD degrees in Computer Science and Engineering in the Chinese University of Hong Kong (CUHK) in 2002, 2004 and 2008, respectively. In 2004-2005, he worked as a research and development assistant under an R&D project funded by ITF and a local industrial company called Lifewood.

He received 38 awards. He published 104 conference papers (e.g., SIGMOD, SIGKDD, VLDB, ICDE and ICDM), 38 journal/chapter papers (e.g., TODS, DAMI, TKDE, VLDB journal and TKDD) and 1 book. He reviewed papers from conferences and journals related to data mining and database, including VLDB conference, SIGMOD, TODS, VLDB Journal, TKDE, TKDD, ICDE, SIGKDD, ICDM, DAMI, DaWaK, PAKDD, EDBT and IJDWM. He is a program committee member of conferences, including SIGMOD, VLDB, ICDE, KDD, ICDM and SDM, and a referee of journals, including TODS, VLDBJ, TKDE, TKDD, DAMI and KAIS.

His research interests include database, data mining and artificial intelligence.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Hervé Lombaert
Associate Professor
ETS Montreal, Canada

Abstract:
How to analyze the shapes of complex organs, such as the highly folded surface of the brain? This talk will show how spectral shape analysis can benefit general learning problems where data fundamentally lives on surfaces. We exploit spectral coordinates derived from the Laplacian eigenfunctions of shapes. Spectral coordinates have the advantage over Euclidean coordinates, to be geometry aware, invariant to isometric deformations, and to parameterize surfaces explicitly. This change of paradigm, from Euclidean to spectral representations, enables a classifier to be applied *directly* on surface data, via spectral coordinates. Brain matching and learning of surface data will be shown as examples. The talk will focus, first, on the spectral representations of shapes, with an example on brain surface matching; second, on the basics of geometric deep learning; and finally, on the learning of surface data, with an example on automatic brain surface parcellation.

Biography:
Hervé Lombaert (和偉 隆巴特/和伟 隆巴特) is an Associate Professor at ETS Montreal, Canada, where he holds a Canada Research Chair in Shape Analysis in Medical Imaging. His research focuses on the statistics and analysis of shapes in the context of machine learning and medical imaging. His work on graph analysis has impacted the performance of several applications in medical imaging, from the early image segmentation techniques with graph cuts, to recent surface analysis with spectral graph theory and graph convolutional networks. Hervé has authored over 70 papers, 5 patents, and earned several awards, such as the IPMI Erbsmann Prize. He had the chance to work in multiple centers, including Inria Sophia-Antipolis (France), Microsoft Research (Cambridge, UK), Siemens Corporate Research (Princeton, NJ), McGill University (Canada), and the University of Montreal (Canada).

More at: https://profs.etsmtl.ca/hlombaert

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. QIN Jing
Centre for Smart Health
School of Nursing
The Hong Kong Polytechnic University

Abstract:
Deep learning has achieved remarkable success in various medical image analysis tasks. No matter the past, present, or the foreseeable future, one of the main obstacles that prohibits deep learning models from being successfully developed and deployed in clinical settings is the scarcity of training data. In this talk, we shall review, as well as rethink, our long experience in investigating how to enhance representation capability of deep learning models to achieve satisfactory performance under limited training data. Based on our experience, we attempt to identify and sort out the evolution trajectory of applying deep leaning to medical image analysis, somehow reflecting the development path of deep learning itself beyond the context of our specific applications. The models we developed, at least in our experience, are both effects and causes: effects of the clinical challenges we faced and the technical frontiers at that time; causes, if they are really useful and inspiring, of following more advanced models that are capable of addressing their limitations. To the end, by rethinking such an evolution, we can identify some future directions that deserve to be further studied.

Biography:
QIN, Jing (Harry) is currently an associate professor in Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University. His research focuses on creatively leveraging advanced virtual/augmented reality (VR/AR) and artificial intelligence (AI) techniques in healthcare and medicine applications and his achievements in relevant areas has been well recognized by the academic community. He won the Hong Kong Medical and Health Device Industries Association Student Research Award for his PhD study on VR-based simulation systems for surgical training and planning. He won 5 best paper awards for his research on AI-driven medical image analysis and computer-assisted surgery. He served as a local organization chair for MICCAI 2019, program committee members for AAAI, IJCAI, MICCAI, etc., speakers for many conferences, seminars, and forums, and referees for many prestigious journals in relevant fields.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Dr. Xi Zheng
Director of Intelligent Systems Research Group
Macquarie University, Australia

Abstract:
Autonomous driving has shown great potential to reform modern transportation. Yet its reliability and safety have drawn a lot of attention and concerns. Compared with traditional software systems, autonomous driving systems (ADSs) often use deep neural networks in tandem with logic-based modules. This new paradigm poses unique challenges for software testing. Despite the recent development of new ADS testing techniques, it is not clear to what extent those techniques have addressed the needs of ADS practitioners. To fill this gap, we have published a few works and I will present some of them. The first work is to reduce and prioritize test for multi-module autonomous driving systems (Accepted in FSE’22). The second work is to conduct comprehensive study to identify the current practices, needs and gaps in testing autonomous driving systems (Accepted also in FSE’22). The third work is to analyse the robustness issues in the deep learning driving models (Accepted in PerCom’20). The fourth work is to generate test cases from traffic rules for autonomous driving models (Accepted in TSE’22). I will also cover some ongoing and future work in autonomous driving systems.

Biography:
Dr. Xi Zheng received the Ph.D. in Software Engineering from the University of Texas at Austin in 2015. From 2005 to 2012, he was the Chief Solution Architect for Menulog Australia. He is currently the Director of Intelligent Systems Research Group, Director of International engagement in the School of Computing, Senior Lecturer (aka Associate Professor US) and Deputy Program Leader in Software Engineering, Macquarie University, Australia. His research interests include Internet of Things, Intelligent Software Engineering, Machine Learning Security, Human-in-the-loop AI, and Edge Intelligence. He has secured more than $1.2 million competitive funding in Australian Research Council (Linkage and Discovery) and Data61 (CRP) projects on safety analysis, model testing and verification, and trustworthy AI on autonomous vehicles. He also won a few awards including Deakin Industry Researcher (2016) and MQ Earlier Career Researcher (Runner-up 2020). He has a number of highly cited papers and best conference papers. He serves as PC members for CORE A* conferences including FSE (2022) and PerCom (2017-2023). He also serves as the PC chairs of IEEE CPSCom-2021, IEEE Broadnets-2022 and associate editor for Distributed Ledger Technologies.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Dr. C. Mohan
Distinguished Visiting Professor, Tsinghua University

Abstract:
In this talk, I will first introduce traditional (non-cloud) parallel and distributed database systems. Concepts like SQL and NoSQL systems, data replication, distributed and parallel query processing, and data recovery after different types of failures will be covered. Then, I will discuss how the emergence of the (public) cloud has introduced new requirements on parallel and distributed database systems, and how such requirements have necessitated fundamental changes to the architectures of such systems. I will illustrate the related developments by discussing some of the details of systems like Alibaba POLARDB, Microsoft Azure SQL DB, Microsoft Socrates, Azure Synapse POLARIS, Google Spanner, Google F1, CockroachDB, Amazon Aurora, Snowflake and Google AlloyDB.

Biography:
Dr. C. Mohan is currently a Distinguished Visiting Professor at Tsinghua University in China, a Visiting Researcher at Google, a Member of the inaugural Board of Governors of Digital University Kerala, and an Advisor of the Kerala Blockchain Academy (KBA) and the Tamil Nadu e-Governance Agency (TNeGA) in India. He retired in June 2020 from being an IBM Fellow at the IBM Almaden Research Center in Silicon Valley. He joined IBM Research (San Jose, California) in 1981 where he worked until May 2006 on several topics in the areas of database, workflow, and transaction management. From June 2006, he worked as the IBM India Chief Scientist, based in Bangalore, with responsibilities that relate to serving as the executive technical leader of IBM India within and outside IBM. In February 2009, at the end of his India assignment, Mohan resumed his research activities at IBM Almaden. Mohan is the primary inventor of the well-known ARIES family of database recovery and concurrency control methods, and the industry-standard Presumed Abort commit protocol. He was named an IBM Fellow, IBM’s highest technical position, in 1997 for being recognized worldwide as a leading innovator in transaction management. In 2009, he was elected to the United States National Academy of Engineering (NAE) and the Indian National Academy of Engineering (INAE). He received the 1996 ACM SIGMOD Edgar F. Codd Innovations Award in recognition of his innovative contributions to the development and use of database systems. In 2002, he was named an ACM Fellow and an IEEE Fellow. At the 1999 International Conference on Very Large Data Bases (VLDB), he was honored with the 10 Year Best Paper Award for the widespread commercial, academic and research impact of his ARIES work, which has been extensively covered in textbooks and university courses. From IBM, Mohan received 2 Corporate and 8 Outstanding Innovation/Technical Achievement Awards. He is an inventor on 50 patents. He was named an IBM Master Inventor in 1997. Mohan worked very closely with numerous IBM product and research groups, and his research results are implemented in numerous IBM and non-IBM prototypes and products like DB2, MQSeries, WebSphere, Informix, Cloudscape, Lotus Notes, Microsoft SQLServer, Sybase and System Z Parallel Sysplex. During the last many years, he focused on Blockchain, AI, Big Data and Cloud technologies (https://bit.ly/sigBcP, https://bit.ly/CMoTalks, https://bit.ly/CMgMDS). Since 2017, he has been an evangelist of permissioned blockchains and the myth buster of permissionless blockchains. During 1H2021, Mohan was the Shaw Visiting Professor at the National University of Singapore (NUS) where he taught a seminar course on distributed data and computing. In 2019, he became an Honorary Advisor to TNeGA of Chennai for its blockchain and other projects. In 2020, he joined the Advisory Board of KBA of India.
Since 2016, he has been a Distinguished Visiting Professor of China’s prestigious Tsinghua University in Beijing. In 2021, he was inducted as a member of the inaugural Board of Governors of the new Indian university Digital University Kerala (DUK). Mohan launched his consulting career by becoming a Consultant to Microsoft’s Data Team in October 2020. In March 2022, he became a consultant at Google with the title of Visiting Researcher. He has been on the advisory board of IEEE Spectrum and has been an editor of VLDB Journal, and Distributed and Parallel Databases. In the past, he has been a member of the IBM Academy of Technology’s Leadership Team, IBM’s Research Management Council, IBM’s Technical Leadership Team, IBM India’s Senior Leadership Team, the Bharti Technical Advisory Council, the Academic Senate of the International Institute of Information Technology in Bangalore, and the Steering Council of IBM’s Software Group Architecture Board. Mohan received his PhD in computer science from the University of Texas at Austin in 1981. In 2003, he was named a Distinguished Alumnus of IIT Madras from which he received a B.Tech. in chemical engineering in 1977. Mohan is a frequent speaker in North America, Europe and Asia. He has given talks in 43 countries. He is highly active on social media and has a huge following. More information can be found in the Wikipedia page at https://bit.ly/CMwIkP and his homepage at https://bit.ly/CMoDUK.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Anupam Chattopadhyay
Associate Professor, NTU

Abstract:
The continued scaling of horizontal and vertical physical features of silicon-based complementary metal-oxide-semiconductor (CMOS) transistors, termed as “More Moore”, has a limited runway and would eventually be replaced with “Beyond CMOS” technologies. There has been a tremendous effort to follow Moore’s law but it is currently approaching atomistic and quantum mechanical physics boundaries. This has led to active research in other non-CMOS technologies such as memristive devices, carbon nanotube field-effect transistors, quantum computing, etc. Several of these technologies have been realized on practical devices with promising gains in yield, integration density, runtime performance, and energy efficiency. Their eventual adoption is largely reliant on the continued research of Electronic Design Automation (EDA) tools catering to these specific technologies. Indeed, some of these technologies present new challenges to the EDA research community, which are being addressed through a series of innovative tools and techniques. In this tutorial, we will particularly cover the two phases of EDA flow, logic synthesis, and technology mapping, for two types of emerging technologies, namely, in-memory computing and quantum computing.

Biography:
Anupam Chattopadhyay received his B.E. degree from Jadavpur University, India, MSc. from ALaRI, Switzerland, and Ph.D. from RWTH Aachen in 2000, 2002, and 2008 respectively. From 2008 to 2009, he worked as a Member of Consulting Staff in CoWare R&D, Noida, India. From 2010 to 2014, he led the MPSoC Architectures Research Group in RWTH Aachen, Germany as a Junior Professor. Since September 2014, Anupam was appointed as an Assistant Professor in SCSE, NTU, where he got promoted to Associate Professor with Tenure from August 2019. Anupam is an Associate Editor of IEEE Embedded Systems Letters and series editor of Springer Book Series on Computer Architecture and Design Methodologies. Anupam received Borcher’s plaque from RWTH Aachen, Germany for outstanding doctoral dissertation in 2008, nomination for the best IP award in the ACM/IEEE DATE Conference 2016 and nomination for the best paper award in the International Conference on VLSI Design 2018 and 2020. He is a fellow of Intercontinental Academia and a senior member of IEEE and ACM.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Professor Peter J. Stuckey
Professor, Department of Data Science and Artificial Intelligence
Monash University

Abstract:
Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy. A commonly criticised point, however, is that the resulting trees may not necessarily be the best representation of the data in terms of accuracy and size. In recent years, this motivated the development of optimal classification tree algorithms that globally optimise the decision tree in contrast to heuristic methods that perform a sequence of locally optimal decisions.
In this talk I will explore the history of building decision trees, from greedy heuristic methods to modern optimal approaches.
In particular I will discuss a novel algorithm for learning optimal classification trees based on dynamic programming and search. Our algorithm supports constraints on the depth of the tree and number of nodes. The success of our approach is attributed to a series of specialised techniques that exploit properties unique to classification trees. Whereas algorithms for optimal classification trees have traditionally been plagued by high runtimes and limited scalability, we show in a detailed experimental study that our approach uses only a fraction of the time required by the state-of-the-art and can handle datasets with tens of thousands of instances, providing several orders of magnitude improvements and notably contributing towards the practical realisation of optimal decision trees.

Biography:
Professor Peter J. Stuckey is a Professor in the Department of Data Science and Artificial Intelligence in the Faculty of Information Technology at Monash University. Peter Stuckey is a pioneer in constraint programming and logic programming. His research interests include: discrete optimization; programming languages, in particular declarative programing languages; constraint solving algorithms; path finding; bioinformatics; and constraint-based graphics; all relying on his expertise in symbolic and constraint reasoning. He enjoys problem solving in any area, having publications in e.g. databases, election science, system security, and timetabling, and working with companies such as Oracle and Rio Tinto on problems that interest them.

Peter Stuckey received a B.Sc and Ph.D both in Computer Science from Monash University in 1985 and 1988 respectively. Since then he has worked at IBM T.J. Watson Research Labs, the University of Melbourne and Monash University. In 2009 he was recognized as an ACM Distinguished Scientist. In 2010 he was awarded the Google Australia Eureka Prize for Innovation in Computer Science for his work on lazy clause generation. He was awarded the 2010 University of Melbourne Woodward Medal for most outstanding publication in Science and Technology across the university. In 2019 he was elected as an AAAI Fellow. and awarded the Association of Constraint Programming Award for Research Excellence. He has over 125 journal and 325 conference publications and 17,000 citations with an h-index of 62.

Enquiries: Mr. Jeff Liu at Tel. 3943 0624

Speaker:
Prof. CAI Shaowei
Institute of Software
Chinese Academy of Sciences

Abstract:
Satisfiability Modulo Theories (SMT) is the problem of deciding the satisfiability of a first order logic formula with respect to certain background theories. SMT solvers have become important formal verification engines, with applications in various domains. In this talk, I will introduce the basis of SMT solving and present our work on improving a famous SMT solver Z3, leading to Z3++, which has won 2 Gold Medals out of 6 from SMT Competition 2022.

Biography:
Shaowei Cai is a professor in Institute of Software, Chinese Academy of Sciences. He has obtained his PhD from Peking University in 2012, with Doctoral Dissertation Award. His research focus on constraint solving (particularly SAT, SMT, and integer programming), combinatorial optimization, and formal verification, as well as their applications in industries. He has won more than 10 Gold Medals from SAT and SMT Competitions, and the Best Paper Award of SAT 2021 conference.

Join Zoom Meeting:
https://cuhk.zoom.us/j/99411951727

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Prof. Hai Zhou
Associate Professor, Department of Electrical and Computer Engineering
Northwestern University

Abstract:
With the increasing cost and complexity in semiconductor hardware designs, circuit IP protection has become an important and challenging problem in hardware security. Logic encryption is a promising technique that modifies a sensitive circuit to a locked one with a password, such that only authorized users can access it. During its history of more than 20 years, many different attacks and defenses have been designed and proposed. In this talk, after a brief introduction to logic encryption, I will present important attacking and defending techniques in the field. Especially, the focus will be on the few key attacks and defenses created in NuLogiCS group at Northwestern.

Biography:
Hai Zhou is the director of the NuLogiCS Research Group in the Electrical and Computer Engineering at Northwestern University and a member of the Center for Ultra Scale Computing and Information Security (CUCIS). His research interest is on Logical Methods for Computer Systems (LogiCS), where logics is used to construct reactive computer systems (in the form of hardware, software, or protocol) and to verify their properties (e.g. correctness, security, and efficiency). In other words, he is interested in algorithms, formal methods, optimization, and their applications to security, machine learning, and economics.

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Dr. Baoyuan WU
Associate Professor, School of Data Science
The Chinese University of Hong Kong, Shenzhen

Abstract:
In this talk, Dr. Wu will review the development of backdoor learning and his lastest works on backdoor attack and defense. The first is the backdoor attack with sample-specific triggers, which can bypass most existing defense methods, as they are mainly developed for defending against sample-agnostic triggers. Then, he will introduce two effective backdoor defense methods which could preclude the backdoor injection during the training process, through exploring some intrinsic properties of poisoned samples. Finally, he will introduce BackdoorBench, which is a comprehensive benchmark containing mainstream backdoor attack and defense methods, as well as 8,000 pairs of attack-defense evaluations, several interesting findings and analysis. It was recently released at “What is BackdoorBench? ”

Biography:
Dr. Baoyuan Wu is an Associate Professor of School of Data Science, the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), and the director of the Secure Computing Lab of Big Data, Shenzhen Research Institute of Big Data (SRIBD). His research interests are AI security and privacy, machine learning, computer vision and optimization. He has published 50+ top-tier conference and journal papers, including TPAMI, IJCV, NeurIPS, CVPR, ICCV, ECCV, ICLR, AAAI. He is currently serving as an Associate Editor of Neurocomputing, Area Chair of NeurIPS 2022, ICLR 2022/2023, AAAI 2022.

Join Zoom Meeting:
https://cuhk.zoom.us/j/91408751707

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Dr. Li Zhenguo
Director, AI Theory Lab
Huawei Noah’s Ark Lab, Hong Kong

Abstract:
Noah’s Ark Lab is the AI research center for Huawei, with the mission of making significant contribution to both the company and society through innovation in artificial intelligence (AI), data mining and related fields. Our AI theory team focuses on the fundamental research in machine learning, including cutting-edge theories and algorithms such as out-of-distribution (OoD) generalization and controllable generative modeling, and disruptive applications such as self-driving. In this talk, we will present some of our progresses in out-of-distribution generalization, including OoD-learnable theories and model selection, understanding and quantification of OoD properties of various benchmark datasets, and related applications. We will also highlight some key challenges for future studies.

Biography:
Zhenguo Li is currently the director of the AI Theory Lab in Huawei Noah’s Ark Lab, Hong Kong. Before joining Huawei Noah’s Ark lab, he was an associate research scientist in the department of electrical engineering, Columbia University, working with Prof. Shih-Fu Chang. He received BS and MS degrees in mathematics at Peking University, and PhD degree in machine learning at The Chinese University of Hong Kong, advised by Prof. Xiaoou Tang. His current research interests include machine learning and its applications.

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Prof. Au, Kwok Wai Samuel
Professor, Department of Mechanical and Automation Engineering, CUHK
Professor, Department of Surgery, CUHK
Co-Director, Chow Yuk Ho Technology Centre for Innovative Medicine, CUHK
Director, Multiscale Medical Robotic Center, InnoHK

Abstract:
Over the past decades, a wide range of bio-inspired legged robots have been developed that can run, jump, and climb over a variety of challenging surfaces. However, in terms of maneuverability they still lag far behind animals. Animals can effectively use their mechanical body and external appendages (such as tails) to achieve spectacular maneuverability, energy efficient locomotion, and robust stabilization to large perturbations which may not be easily attained in the existing legged robots. In this talk, we will present our efforts on the development of innovative legged robots with greater mobility/efficiency/robustness, comparable to its biological counterpart. We will discuss the fundamental challenges in legged robots and demonstrate the feasibility of developing such kinds of agile systems. We believe our solutions could potentially lead to more efficient legged robot design and give the legged robot animal-like mobility and robustness. Furthermore, we will also present our robotic development on surgery domain and show how these technologies can be integrated with legged robots to create novel teleoperated legged mobile manipulators for service and construction applications.

Biography:
Dr. Kwok Wai Samuel Au is currently a Professor of the Department of Mechanical and Automation Engineering and Department of Surgery (by courtesy) at CUHK, and the Founding Director of Multiscale Medical Robotics Center, InnoHK. In Sept 2019, Dr. Au found Cornerstone Robotics and has been serving as the president of the company, aiming to create affordable surgical robotic solution. Dr. Au received the B.Eng. and M.Phil degrees in Mechanical and Automation Engineering from CUHK in 1997 and 1999, respectively and completed his Ph.D. degree in Mechanical Engineering at MIT in 2007. During his PhD study, Prof. Hugh Herr, Dr. Au, and other colleagues from MIT Biomechatronics group co-invented the MIT Powered Ankle-foot Prosthesis.

Before joining CUHK(2016), he was the manager of Systems Analysis of the New Product Development Department at Intuitive Surgical, Inc. At Intuitive Surgical, he co-invented and was leading the software and control algorithm development for the FDA cleared da Vinci Si Single-Site surgical platform (2012), Single-Site Wristed Needle Driver (2014), and da Vinci Xi Single-Site surgical platform (2016). He was also a founding team member for the early development of Intuitive Surgical’s FDA cleared robot-assisted catheter system, da Vinci ION system from 2008 to 2012.

Dr. Au co-authored over 60 peer-reviewed manuscripts and conference journals, 17 granted US patents/EP, and 3 pending US Patents. He has won numerous awards including the first prize in the American Society of Mechanical Engineers (ASME) Student Mechanism Design Competition in 2007, Intuitive Surgical Problem Solving Award in 2010, and Intuitive Surgical Inventor Award in 2011.

Enquiries: Ms. Karen Chan at Tel. 3943 8439