Singapore Programming Languages Summit 2025
The SG PL Summit is a community event that aims to bring together researchers, students, and practitioners in programming languages and related areas (including, but not limited to formal methods, verification, systems, compilers, and software engineering) to share ideas, ongoing work, and future directions. It’s a great opportunity to connect with others in the local PL community, learn about exciting projects, and build new collaborations.
Type: Conferences & Symposiums. Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. SMU Faculty & Staff. Incoming PG Students. Academic Community. Partners.
Monday, November 24, 2025, 9:00 AM – 5:00 PM.
Singapore Management University, Room SR B1-01 (Basement 1)
Yong Pung How School of Law, 55 Armenian St, Singapore 179943.
For more info visit sg-pl-summit.github.io. Toward Generalist Anomaly Detectors
Anomaly Detection (AD) is essential across manufacturing, healthcare, and security applications, yet existing deep learning–based approaches remain highly specialized: they require dataset-specific training and struggle to generalize to unseen anomaly types or new domains. Real-world anomalies are rare, heterogeneous, and inherently unpredictable, motivating the development of generalist anomaly detectors capable of operating across diverse settings without task-specific retraining or large amounts of target data. This dissertation aims to advance the generalization capability of AD models through a progressive research trajectory spanning three increasingly challenging supervision regimes, culminating in a unified pathway from open-set supervised AD to few-shot generalist AD and ultimately zero-shot AD.
Subtitle: PhD Dissertation Proposal by ZHU Jiawen. Contact: scisseminars@smu.edu.sg. Speaker Details:
ZHU Jiawen
PhD Candidate
School of Computing and Information Systems
Singapore Management University, Jiawen Zhu is currently a fourth-year PhD candidate at Singapore Management University and supervised by Prof. Guansong Pang. She has published and presented multiple papers at top venues, including CVPR and ICCV. Her research interests lie in the field of computer vision and open-world learning, particularly in generalist anomaly detection. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UOVBKSUk0RloySEtIQVdSSlNPRks3NTQ1Uy4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Monday, November 24, 2025, 1:00 PM – 2:00 PM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. OSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching
Offline Learning from Observation (LfO) focuses on enabling agents to imitate expert behavior using datasets that contain only expert state trajectories and separate transition data with suboptimal actions. This setting is both practical and critical in real-world scenarios where direct environment interaction or access to expert action labels is costly, risky, or infeasible. Most existing LfO methods attempt to solve this problem through state or state-action occupancy matching. They typically rely on pretraining a discriminator to differentiate between expert and non-expert states, which could introduce errors and instability—especially when the discriminator is poorly trained. While recent discriminator-free methods have emerged, they generally require substantially more data, limiting their practicality in low-data regimes. In this paper, we propose IOSTOM (Imitation from Observation via State Transition Occupancy Matching), a novel offline LfO algorithm designed to overcome these limitations. Our approac…
Subtitle: Pre-Conference Talk by PHAM Quang Anh. Contact: scisseminar@smu.edu.sg. Speaker Details: , PHAM Quang Anh
PhD Student
School of Computing and Information Systems
Singapore Management University, Quang Anh PHAM is a first-year PhD student in Computer Science at SMU School of Computing and Information Systems, supervised by Associate Prof Akshat Kumar and Assistant Prof Mai Anh Tien. His research interests are Artificial Intelligence (Imitation Learning, Reinforcement Learning and Heuristic Search), Operations Research (Routing and Scheduling problems), and Combinatorial Optimization… RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UNTNVVE9KMVJERFRLSlk0OTFEWVdIREQwOC4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public.
Tuesday, November 25, 2025, 11:30 AM – 12:00 PM.
Meeting room 5.1, Level 5. School of Computing and Information Systems 1,
Singapore Management University, 80 Stamford Road, Singapore 178902.
For more info visit computing.smu.edu.sg. Attacking Numerical Stability in Machine Learning
Numerical instability in machine learning arises when tiny changes in input or computational precision cause large, unpredictable shifts in model output, leading to unreliable predictions in domains like healthcare, finance, and autonomous driving. This instability undermines the robustness and trustworthiness of AI systems in real-world settings.
Our research explores how numerical instability itself can be exploited to cause model failures. The first work shows how adding noise to optimization layers (e.g. OptNet) can trigger NaNs and cause complete failure in model inference. The second investigates attacks on Large Vision-Language Models (LVLMs) that induce instability throughout the network, revealing a novel, distinct threat beyond traditional adversarial perturbations. We conclude by highlighting directions for deeper study into this emerging vulnerability.
Subtitle: PhD Dissertation Proposal by WONG Wai Tuck. Contact: scisseminars@smu.edu.sg. Speaker Details:
WONG Wai Tuck
PhD Candidate
School of Computing and Information Systems
Singapore Management University, WONG Wai Tuck is Head of Labs Engineering at watchTowr, where he leads engineering offensive security capabilities. He is also a part-time PhD candidate in the School of Computing and Information Systems in Singapore Management University, co-advised by Arunesh Sinha and Sun Jun. His interest lies in the intersection of machine learning and cybersecurity, primarily looking at novel attack vectors in… RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UOTNUTVFLUkEyWE5MUTdCUjg2QUpOSldPUS4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Wednesday, November 26, 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. Understanding, Detecting, Repairing Software Bugs with Context-Aware Explainable LLMs
Software vulnerabilities are widespread in modern systems, threatening reliability, safety, and maintainability across sectors from healthcare to transportation, and imposing substantial economic burdens and developer effort. Automated Program Repair (APR) aims to mitigate these risks by generating fixes automatically, reducing both time and human effort. Recent Large Language Models (LLMs) have shown promising performance in APR and, in some cases, surpass traditional techniques. However, practical deployment exposes several gaps. First, LLM performance on APR tasks is suboptimal in data-scarce settings. Second, benchmark accuracy alone does not demonstrate genuine bug understanding, and the models’ black box nature hampers human interpretability, undermining trust when stated explanations diverge from the actual fix strategies. Third, domain-specific semantics, such as Rust and C/C++ interoperability and C-to-Rust translation, are underrepresented in general benchmarks, and their specific characteristics re…
Subtitle: PhD Dissertation Proposal by CAI Xuemeng. Contact: scisseminars@smu.edu.sg. Speaker Details: , CAI Xuemeng
PhD Candidate
School of Computing and Information Systems
Singapore Management University, CAI Xuemeng is a third-year PhD candidate and a Research Engineer at the Centre for Research on Intelligent Software Engineering (RISE) at Singapore Management University (SMU). Her research interests focus on software engineering challenges such as automatic program repair, code translation, and the interpretability of Large Language Models. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UN0pWQk1JVUNFR0I3NUFIRDhYNElGTDRMQi4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Thursday, November 27, 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. Recombinant Creativity: Idea Generation, Network Formation, and Innovation Outcomes
This dissertation examines recombinant creativity across cultural production and crowdsourced innovation platforms, focusing on how ideas are generated, collaboratively shaped, and strategically combined to drive innovation. Motivated by the growing importance of idea recombination in film and media industries, the first study investigates how new and existing ideas are recombined to form innovative creative products and how these recombinations affect innovation success. The second study then analyzes how new ideas emerge from the evolving structure and content of idea networks via, tracing how collaborative contributions from both ideators and the crowd shape the development, diversity, and connectivity of ideas on crowdsourcing innovation platforms . Finally, the third study examines how platform design, specifically, identity disclosure in voting systems, affects users’ voting decisions and ideators’ editing and interaction behaviors. Together, these studies provide a comprehensive understanding of recomb…
Subtitle: PhD Dissertation Proposal by LIAW Shao Yi. Contact: scisseminars@smu.edu.sg. Speaker Details:
LIAW Shao Yi
PhD Candidate
School of Computing and Information Systems
Singapore Management University, Shao Yi LIAW is a Ph.D. candidate majoring in Information Systems and Management at the School of Computing and Information Systems, Singapore Management University, supervised by Associate Professor Qian TANG. Her research interests include product innovation and knowledge networks. Her work has appeared in The Workshop on E-Business amongst others. RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UOFRWN0pTTTRVUkpQUFJYRFY2VzBXWTA0My4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Friday, November 28, 2025, 2:00 PM – 3:00 PM.
Meeting room 4.4, Level 4. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems
Existing GFlowNet-based methods for vehicle routing problems (VRPs) typically employ Trajectory Balance (TB) to achieve global optimization but often neglect important aspects of local optimization. While Detailed Balance (DB) addresses local optimization more effectively, it alone falls short in solving VRPs, which inherently require holistic trajectory optimization. To address these limitations, we introduce the Hybrid-Balance GFlowNet (HBG) framework, which uniquely integrates TB and DB in a principled and adaptive manner by aligning their intrinsically complementary strengths. Additionally, we propose a specialized inference strategy for depot-centric scenarios like the Capacitated Vehicle Routing Problem (CVRP), leveraging the depot node's greater flexibility in selecting successors. Despite this specialization, HBG maintains broad applicability, extending effectively to problems without explicit depots, such as the Traveling Salesman Problem (TSP). We evaluate HBG by integrating it into two established…
Subtitle: Pre-Conference Talk by ZHANG Ni. Contact: scisseminar@smu.edu.sg. Speaker Details: , ZHANG Ni
PhD Student
School of Computing and Information Systems
Singapore Management University, Zhang Ni is a PhD in Computer Science student at Singapore Management University, under the supervision of Assistant Professor Cao Zhiguang. Her research centers on combinatorial optimization with an emphasis on developing learning-driven algorithms for complex routing problems. Recently, she has been investigating generative flow networks (GFlowNets) to achieve more effective and generalizable solutions… RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTacjffrphqhDrJfv1DjxSmNUMDFWREFYRk0yNFRWVEdTUTUyTk5MUjYwRS4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public.
Friday, November 28, 2025, 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.