Events
Feedback-guided representation learning for reasoning in the dynamic physical world
ISTD PhD Oral Defence Seminar by Mark He Huang – Modern AI systems often struggle in physical environments where observations are incomplete, noisy and constantly changing. This seminar presents a feedback-guided representation learning framework that helps AI systems revise what they know, maintain useful representations over time and generate physically plausible outcomes. The work spans machine unlearning, object-centric 3D visual memory and simulator-guided video generation, with the broader aim of enabling more reliable reasoning in the dynamic physical world.
Towards generalisable intelligence: From pre-training to chain-of-thought and interventional exploration
ISTD PhD Oral Defence Seminar by Wang Tianduo – This thesis studies how large language models (LLMs) generalise under distribution shift.
Shaping inductive bias in foundation models: A signal-centric perspective on reasoning and learning dynamics
ISTD PhD Oral Defence Seminar by Jiaxi Li – Foundation models have demonstrated strong reasoning capabilities, yet their behaviours can vary substantially depending on how learning signals are constructed and exposed during training.
Energy-aware edge AI accelerator design for applications from CNNs to LLMs
ISTD PhD Oral Defence Seminar by Dongrui Li – The dissertation investigates four AI accelerator design directions, each validated through tapeout prototypes. Spiking Neural Network (SNN) accelerators are explored with in network computing.
Master of Architecture information session for intake 2026
The SUTD’s Master of Architecture (MArch) programme offers a future-forward professional degree programme, highlighting design and research for sustainability and the digital transformation of the architectural profession. The programme launches the careers of leaders in architecture by emphasizing independent critical thinking in a thesis project, supported by close collaborations with faculty on cutting-edge research.
Towards trustworthy and explainable AI for multimodal hate content moderation
ISTD PhD Oral Defence Seminar by Hee Ming Shan – The proliferation of hateful multimodal content, particularly in the form of hateful memes, poses significant threats to online safety and social cohesion. Although deep learning systems, especially vision-language models, are essential to automated multimodal content moderation, they operate as black boxes, offering limited explainability into their decision-making processes.
Software-hardware co-design for energy-efficient neural network accelerators
ISTD PhD Oral Defence Seminar by Tomomasa Yamasaki – This dissertation proposes an integrated research framework that spans algorithm-level network evaluation, hardware-aware optimisation, and cycle-accurate performance simulation.
Explaining graph-based misinformation detection models
ISTD PhD Oral Defence Seminar by Chin Wai Kit Daniel – Social media and social networking platforms have greatly connected people worldwide and democratised information creation and propagation by facilitating seamless and almost instantaneous information sharing between people and communities.
Leveraging out of distribution testing to build robust machine learning systems
ISTD PhD Oral Defence Seminar by Sai Sathiesh Rajan – This dissertation serves to remind us of the importance of thoroughly testing machine learning models before deploying them as they can cause societal, economical and reputational damage.
Beyond scale: efficient pre-training and controllable post-training for language models
ISTD PhD Oral Defence Seminar by Zeng Guangtao – Language models are foundational to modern artificial intelligence, but their development is often constrained by challenges in efficiency, controllability, and reasoning. In this thesis, we aim to address these limitations by introducing advanced paradigms at both the pre-training and post-training stages.
