Events
Overcoming the limitations of autoregressive and non-autoregressive neural models
ISTD PhD Oral Defense Seminar by Haoran Li – Language models are critical to the advancement of natural language processing and general artificial intelligence. In this thesis, we aim to address the limitations of language models, particularly focusing on the exposure bias in Autoregressive (AR) models and the label bias in Non-Autoregressive (NAR) models.
An introduction of cybersecurity in investment banking: an overview of digital signatures
ISTD COIL Seminar by Fan Liu & Felix Tong – This session will give you an overview of how technology, especially cybersecurity, is being adapted at Morgan Stanley. Speakers will then deep dive into the topic of digital signatures – the origin, history, and more importantly its current application in the banking industry and latest developments.
Towards effective, robust, and continual multi-modal learning
ISTD PhD Oral Defense Seminar by Li Xu – In the ever-evolving field of artificial intelligence (AI), deep learning has emerged as a pivotal technique driving remarkable advancements across various domains. Among its many branches, multi-modal learning stands out as a particularly significant approach, which involves integrating and processing information from multiple modalities of data, such as visual content and language information, to enhance the capabilities of AI systems.
Urban Larsson (IIT Bombay, India) – The Fundamental Theorem of Normal Play
Urban Larsson (IIT Bombay, India) – The Fundamental Theorem of Normal Play
Public Lecture: “The Urban Lab : Innovating for Density and Scarcity”
The talk will focus on how we have been addressing two of the most difficult issues that confront us – an increasingly dense environment and the scarcity of fundamental resources such as land, water and energy. The lecture provides useful insights for all who live and work in Singapore and are interested to contribute to making ours an even more liveable, sustainable and vibrant city.
Yuanwei Liu (Queen Mary University of London) – Near-field Communications: What Will be Different?
Yuanwei Liu (Queen Mary University of London) – Near-field Communications: What Will be Different?
LKY CIC Brown Bag Lunchtime Talk: “Modelling Cities as Complex Adaptive Systems: CitySIM – An Agent-Based System for Modelling and Simulating Cities”
Synopsis Cities are complex entities that consists of many interacting systems. Cities are expected to grow in size and diversity, face diminishing
Modelling and design of assemblies with discrete equivalence classes
ISTD PhD Oral Defense Seminar by Rulin Chen – An assembly comprises parts joined together to achieve a specific form or functionality. Compared to monolithic objects, assemblies have many benefits in terms of fabrication, transportation, and adaptability. Parts of assemblies are always geometrically simple to fabricate with digital techniques, can be efficiently packed for transportation, and offer adaptability through flexible replacement or modification. Hence, assemblies are widely used in our daily lives that most of our consumer products, industry machines, and architectural structures are assemblies.
LKY CIC Brown Bag Lunchtime Talk: “Using citizen science for a deeper understanding of the urban built environment”
Synopsis This presentation explores the use of citizen science; highlighting the potential for this underutilised methodology to create better, data
Leveraging pre-trained language models for social geolocation
ISTD PhD Oral Defense Seminar by Menglin Li – Social media has become an integral part of daily life, leading to an explosion of social data. Geographical information within social media is essential for applications such as location-based analysis, recommendations, and targeted advertising. However, such information is sparse, prompting the exploration of mining it from social media data.
