Events

Neural networks are known to be over-parametrized and sparse models have been shown to perform as well as dense models over a range of image and language processing tasks. However, while compact representations and model compression methods have been applied to speech tasks, sparsification techniques have rarely been used on text-to-speech (TTS) models. We seek to characterize the impact of selected sparse techniques on the performance and model complexity. […]

3D digital human has been widely used in fields like virtual reality, fashion, and film/game production. Traditionally, creating and animating digital humans requires skilled engineers and expensive equipment, typically accessible only to large companies. Thus, developing deep learning tools to democratize the creation and animation of digital humans is urgently needed. […]

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. […]

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. The primary objective of multi-modal learning is to leverage the complementary information present in different modalities to achieve better performance than using any single modality alone, mimicking the way humans perceive and understand the world. […]

Urban Larsson (IIT Bombay, India) – The Fundamental Theorem of Normal Play

Yuanwei Liu (Queen Mary University of London) – Near-field Communications: What Will be Different?

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. […]

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. […]

Howard H. Yang (Zhejiang University) – Federated Learning Over the Air: A Tale of Interference

Wang Hai (Singapore Management University) – Data-Driven Methods and Applications in Smart Cities