Towards Efficient Deep Learning on Resource-Constrained Embedded Devices
The widespread adoption of deep learning has enabled breakthroughs in perception and decision-making tasks across domains such as vision, speech, and human activity recognition. However, deploying such capabilities on resource-constrained embedded devices—like microcontrollers and edge sensors—remains a major challenge due to the tight limits on memory, compute, and energy. These challenges are particularly severe in on-device settings, where models must operate autonomously, adapt in real time, and process data locally without access to powerful cloud infrastructure. This thesis investigates two complementary research directions to address these challenges. First, it proposes a bottom-up design paradigm that builds accurate, ultra-compact models from scratch using diversity-driven ensemble techniques and lightweight fusion mechanisms. Second, it explores robust, unsupervised adaptation strategies to maintain model accuracy in the presence of domain shifts. Together, these contributions aim to establish a pra…
Subtitle: PhD Dissertation Proposal by MA Xiao. Contact: scisseminars@smu.edu.sg. Speaker Details:
MA Xiao
PhD Candidate
School of Computing and Information Systems
Singapore Management University, MA Xiao is a third-year Ph.D. candidate in Computer Science at the School of Computing and Information Systems under the supervision of Associate Professor Dong MA. His research focuses on developing efficient machine learning algorithms for resource-constrained devices. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UQURJWTY4M1pJWkhXT1FKQU9COVVJTlkzRyQlQCNjPTEu. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Wednesday, August 6, 2025, 3:00 AM – 4:00 AM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. From Single-Agent Reliability to Multi-Agent Synergy: A Software Engineering Perspective towards Deployable Autonomous Agents
Autonomous agents, powered by Deep Reinforcement Learning (DRL) and Large Language Models (LLMs), hold immense promise. However, their transition from controlled simulations to the real world is hindered by critical challenges in reliability. Ensuring these agents are safe, effective, and engaging in productive teamwork, requires a rigorous software engineering approach that goes beyond traditional evaluation methods. This dissertation addresses this gap by developing a suite of novel frameworks for the comprehensive testing of autonomous agents. We address agent safety, policy optimality. Building on this foundation of single-agent reliability, we extend our focus to multi-agent collaboration. We provide a systematic review of LLM-Based Multi-Agent (LMA) systems in software engineering and propose a comprehensive research agenda to guide their future development.
Subtitle: PhD Dissertation Proposal by HE Junda. Contact: scisseminars@smu.edu.sg. Speaker Details:
HE Junda
PhD Candidate
School of Computing and Information Systems
Singapore Management University, Junda HE is a Ph.D. candidate in Computer Science at the School of Computing and Information Systems, Singapore Management University, under the supervision of Professor David LO. His research focuses on various aspects of Large Language Models for Software Engineering (LLM4SE) and Trustworthy AI, with outcomes published in premier venues such as ICSE, TOSEM, TSE, and ASE. He also serves as a reviewer… RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UODFTV1lGMDJJVDcySENCOEZMTUgwODdMUS4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Wednesday, August 6, 2025, 3:30 AM – 4:30 AM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. Toward Automatic Testing and Safeguarding for Autonomous Driving Systems
Autonomous Driving Systems (ADSs) represent one of the most complex and promising classes of intelligent systems, with the potential to bring profound societal impact. Due to their safety-critical nature and close interaction with the public, rigorous evaluation is essential to ensure the safety and reliability of ADSs before deployment. Although recent advances in ADS testing have shown promise in identifying corner cases, the vast diversity of driving scenarios and the inherent complexity of ADSs continue to pose major challenges for comprehensive testing and effective safeguarding. This dissertation proposal presents a series of automated techniques designed to address these challenges. Specifically, it introduces: (1) behavior-guided safety testing to explore diverse critical scenarios, (2) evaluation of the robustness of ADSs in making optimal decisions, (3) deadlock avoidance testing for multi-vehicle interactions, and (4) a safeguarding approach for runtime decision repair in ADSs.
Subtitle: PhD Dissertation Proposal by CHENG Mingfei. Contact: scisseminars@smu.edu.sg. Speaker Details:
CHENG Mingfei
PhD Candidate
School of Computing and Information Systems
Singapore Management University, CHENG Mingfei is a Ph.D. candidate in Computer Science at the SMU School of Computing and Information Systems, supervised by Assistant Professor XIE Xiaofei. His research primarily focuses on software engineering for AI-enabled systems, specifically the testing and improvement of autonomous driving systems. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UNUFTUjRNSVg0WVZKNVk4WlI3OVdaTlVOSiQlQCNjPTEu. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Wednesday, August 6, 2025, 9:00 AM – 10:00 AM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. PRISM: To Fortify Widget Based User-App Data Exchanges Using Android Virtualization Framework
PRISM is an UI hardening technique for an Android app to safeguard its widgets against a corrupted kernel. PRISM ensures secure interface rendering and allows for visual authentication, which developers could use to enable user intent confidentiality protection. Our design leverages the recent Android Virtualization Framework with minimal changes to the existing UI framework and graphics subsystem. It is much easier to deploy and use PRISM on Android phones than TrustZone-based secure UI schemes, because the apps are not admitted to the Secure World and retain their full rights to manage and control their own interfaces. We implemented a prototype of PRISM and a test app on Google Pixel 7 and assessed its security, usability and performance. The results validated the strength of its security and show unnoticeable latency in most interface operations.
This is a Pre-Conference talk for The 20th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS 2025).
Subtitle: Pre-Conference Talk by NG Ying Tat. Contact: scisseminar@smu.edu.sg. Speaker Details:
NG Ying Tat
PhD Candidate
School of Computing and Information Systems
Singapore Management University, Ng Ying Tat is a part-time Ph.D. candidate in Computer Science at the School of Computing and Information Systems, Singapore Management University (SMU), under the supervision of Prof Ding Xuhua. His research interest is in Android and ARM System Security Assisted by Hardware Features. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UNE43SktWN0VQWTAwNjRSR0gwQzdIWTI2UCQlQCNjPTEu. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public.
Thursday, August 7, 2025, 2:00 AM – 2:30 AM.
Meeting room 4.4, Level 4. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. SMU Doctor of Engineering (EngD) Virtual Information Session
Infosessions
.
RSVP: . Reserve a seat: https://scispg.smu.edu.sg/acton/media/44865/engdis0825. Type: Information Sessions. Webinar & Online Learning. Subject: Business. Leadership. Operations Management. Organisational Behaviour. Strategic Management. Audience: Professionals. Prospective Student.
Thursday, August 21, 2025, 7:00 PM – 8:00 PM.
Virtual via Zoom
Details will be provided via email upon registration.
MITB Virtual Information Session (Singapore)
Public Events
RSVP: . Reserve a seat: https://scispg.smu.edu.sg/acton/media/44865/mitbisscis0825. Type: Information Sessions. Subject: Analytics for Business, Consumer & Social Insights. Information Technology & Systems. Innovation & Entrepreneurship. Learning & Professional Development. International. Leadership. Operations Management. Organisational Behaviour. Strategic Management. Audience: Public.
Saturday, August 23, 2025, 10:00 AM – 12:00 PM.
Online
This information session will be conducted virtually via Zoom. Please register for the session by clicking on the “Register Now” button that leads you to our event registration form.
MITB Coffee Session (Singapore)
Public Events
.
RSVP: . Reserve a seat: https://scispg.smu.edu.sg/acton/media/44865/mitbcsscis0925. Type: Information Sessions. Subject: Analytics for Business, Consumer & Social Insights. Information Technology & Systems. Innovation & Entrepreneurship. International. Leadership. Learning & Professional Development. Strategic Management. Audience: Public. Professionals. Prospective Student.
Wednesday, September 3, 2025, 7:00 PM – 8:00 PM.
In-Campus
SMU School of Computing and Information Systems
Limited seats available!
Complimentary Starbucks on us!
For more info visit scispg.smu.edu.sg. SCIS Industry Day 2025
This event aims to promote bilateral dialogue between Industry/Public and SCIS exploring opportunities and challenges at technology frontiers of mutual interest. This is achieved with a program by which both sides would hear the state-of-the-art and problems of priority from each other via talks, panels discussion, networking and break-out sessions.
More details at https://computing.smu.edu.sg/newsletter/scis-industry-day-4-september-2025-0?newsletter.
RSVP: . Reserve a seat: https://forms.cloud.microsoft/pages/responsepage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTRhaonc6j4ZJnclQsZzigPJUNFhXVVZZVEU5T1RZMkRRU05PUTE1MjlZRS4u&route=shorturl. Type: Conferences & Symposiums. Social & Networking. Information Sessions. Subject: Information Technology & Systems. Audience: Public. Academic Community. SMU Faculty & Staff. Professionals.
Thursday, September 4, 2025, 8:30 AM – 4:30 PM.
SOSS/CIS Event Lobby, SMU.
For more info visit smu.sg.