Towards Efficient Continual Learning: From Memory Optimization to Foundation Models
Continual learning, also termed lifelong learning, enables machine learning models to incrementally acquire new knowledge while mitigating the degradation of previously learned information--a capability essential for adapting to dynamic, real-world data environments. This dissertation investigates the core challenges of continual learning and extends its application to enhancing training efficiency in the era of foundation models. The first part of this dissertation addresses the constraints of few-shot exemplar storage with a novel compression framework. While leveraging class activation maps to downsample non-discriminative pixels, we introduce an adaptive masking model, optimized through bilevel optimization, to store more exemplars efficiently. The second part focuses on the data dynamics of continual learning. We model continuous distribution shifts using bell-shaped curves to simulate realistic streams. We identify the challenges of non-stationarity and class imbalance in such evolving environments, and…
Subtitle: PhD Dissertation Defense by LUO Zilin. Contact: scisseminars@smu.edu.sg. Speaker Details: , LUO Zilin
PhD Candidate
School of Computing and Information Systems
Singapore Management University, LUO Zilin is a Ph.D. candidate at Singapore Management University, supervised by SUN Qianru. He conducts research on artificial intelligence and machine learning. His research interest lies in continual learning. Before joining SMU, Zilin graduated with a Bachelor’s degree in Electronic Information Engineering from University of Science and Technology of China. He likes running, playing bass and doing… RSVP: . Reserve a seat: https://forms.cloud.microsoft/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9URDVRSU1LUUxaVE1CSVkzSTUyT0RQQ1hRQy4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Monday, May 25, 2026, 10:00 AM – 12:00 PM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. Stance-Linked Provenance: How Voter Identity Disclosure Reshapes Voting and Suggestion Incorporation on Crowdsourcing Platforms
Digital knowledge production on collaborative platforms is governed by the interplay between crowd evaluation and feedback, especially in the generative AI era, when ideas and suggestions can be produced at far greater speed and scale. This study examines how evaluator identity disclosure shapes users’ evaluation and ideators’ incorporation of crowd feedback. Leveraging a design change on TVTropes that shifted voting from anonymous to attributable, we find that identity disclosure reduces both positive and negative evaluations, suggesting lower evaluative participation. We also find that the incorporation of detractor feedback is reduced with identity disclosure, indicating that ideators are less receptive to opposing input when feedback is tied to revealed evaluative stance. These findings reveal a governance trade-off: while identity disclosure enhances accountability and transparency, it simultaneously reduces participation and limits learning from dissent.
This is a Pre-Conference talk for Twenty-second…
Subtitle: Pre-Conference Talk by LIAW Shao Yi. Contact: scisseminar@smu.edu.sg. Speaker Details: , LIAW Shao Yi
PhD Candidate
School of Computing and Information Systems
Singapore Management University, LIAW Shao Yi is a Ph.D. candidate in Information Systems, supervised by Prof. TANG Qian. Her general research interests are in product and human innovation with an emphasis on how individuals generate, evaluate, and refine ideas on digital platforms. RSVP: . Reserve a seat: https://forms.cloud.microsoft/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UM09YNlY1V0k4M0dENjdNQ1UwT1VMU0dXTy4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public.
Thursday, May 28, 2026, 2:00 PM – 2:30 PM.
Meeting room 4.4, Level 4. School of Computing and Information Systems 1,
Singapore Management University, 80 Stamford Road, Singapore 178902.
For more info visit computing.smu.edu.sg. Aligned Multi-View Scripts for Universal Chart-to-Code Generation
Chart-to-code generation converts a chart image into an executable plotting script, enabling faithful reproduction and editable visualizations. Existing methods are largely Python-centric, limiting practical use and overlooking a critical source of supervision: the same chart can be expressed by semantically equivalent scripts in different plotting languages. To fill this gap, we introduce Chart2NCode, a dataset of 176K charts paired with aligned scripts in Python, R, and LaTeX that render visually equivalent outputs, constructed via a metadata-to-template pipeline with rendering verification and human quality checks. Building on a LLaVA-style architecture, we further propose CharLuMA, a parameter-efficient adaptation module that augments the multimodal projector with a language-conditioned mixture of low-rank subspaces, allowing the model to share core chart understanding while specializing code generation to the target language through lightweight routing. Extensive experiments show consistent gains in exec…
Subtitle: Pre-Conference Talk by ZHANG Zhihan. Contact: scisseminar@smu.edu.sg. Speaker Details: , ZHANG Zhihan
PhD Candidate
School of Computing and Information Systems
Singapore Management University, ZHANG Zhihan is a Ph.D. student in Computer Science at the SMU School of Computing and Information Systems, supervised by Prof. LIAO Lizi. Her research focuses on cross-modal reasoning. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTacjffrphqhDrJfv1DjxSmNUNjVaMlVEM1Y5WDNOTFBNUVc0MkpQN1c5Ni4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public.
Thursday, May 28, 2026, 4:30 PM – 5:00 PM.
Meeting room 4.4, Level 4. School of Computing and Information Systems 1,
Singapore Management University, 80 Stamford Road, Singapore 178902.
For more info visit computing.smu.edu.sg. DBA(Tech) Information Session - Tech-Ready Leadership in the Age of AI
Infosessions
.
Term Week: Week. Subject: Careers. Type: Information Sessions. Seminars & Workshops. Audience: Current Student. Reserve a seat: https://smu.sg/DBA_Tech_event. RSVP: .
Thursday, May 28, 2026, 6:30 PM – 9:00 PM.
Hybrid (details will be shared base on registration).
For more info visit smu.sg. DBA(Tech) Information Session: Tech-Ready Leadership in the Age of AI
Infosessions
RSVP: . Reserve a seat: https://scispg.smu.edu.sg/acton/media/44865/dbatmcis0526. Type: Information Sessions. Subject: Information Technology & Systems. Leadership. Audience: Professionals. Public.
Thursday, May 28, 2026, 6:30 PM – 9:00 PM.
Hybrid (details will be shared base on registration).
Designing for “Just Enough”: How Elegance Drives Adoption and Innovation
In an environment saturated with information, products, and interfaces, users increasingly expect designs that are both simple and effective. Elegant Design: A Designer’s Guide to Harnessing Aesthetics examines how the tension between simplicity and complexity can be addressed by conceptualizing elegance as a form of ideal complexity: sufficiently rich to convey meaning, yet clear enough for immediate comprehension. Drawing on research at the intersection of cognitive science, information theory, and art, Luca Landoli demonstrates that aesthetic pleasure is not merely an optional enhancement, but a critical factor guiding decision-making in design, innovation, and product development. Utilizing over 100 visual examples and case studies, the book presents eight actionable strategies: four for enriching designs that lack engagement, and four for simplifying solutions that have become overly complex. This presentation is particularly relevant for scholars and students in information systems, human-computer inter…
Subtitle: Research Seminar by Dr Luca Iandoli. Contact: scisseminars@smu.edu.sg. Speaker Details: , Luca Iandoli
Distinguished Chair and
Dean of the Lesley H. and William L. Collins
College of Professional Studies
St. John’s University, Luca Iandoli is Dean of the Collins College of Professional Studies at St. John’s University. A scholar of collective intelligence, interaction design, and product aesthetics, his work explores how people and organizations make sense of complexity through design. A former Fulbright Visiting Scholar at the MIT Center for Collective Intelligence, he has also served as… RSVP: . Reserve a seat: https://forms.office.com/pages/responsepage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTbOXO7ktpRtBsn62WuekYtpUN0wxN0pDNjcyMEFTSDZKVFY1VThMWVNWVS4u&route=shorturl. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Friday, June 19, 2026, 10:30 AM – 11:30 AM.
Seminar Room 2-5, Level 2. SMU SCIS 2, Singapore 178903.
For more info visit computing.smu.edu.sg.