Site Map | HKU Portal | Staff Intranet |
Zoom Link: https://hku.zoom.us/j/97793742616?pwd=YIyYlokhzOsap3IvbsbwmfaHVHFoin.1 Abstract As Generative AI shifts toward handling massive context windows, the quadratic complexity of Transformer architecture has become a significant bottleneck. State Space Models (SSMs), particularly Mamba, […]
All EEE postgraduate (TPg & RPg) students are welcome! The upcoming “HKU-KAUST Joint Postgraduate Workshop on Computational Imaging 2025” will be held on December 13, 2025, organised by the Computational […]
Click HERE to view the details.
*** Please note that the event has been rescheduled to Monday, December 15, 2025. *** Abstract Space-Air-Ground Integrated Networks (SAGINs), an architecture combining satellites, aerial platforms (like UAVs and High-Altitude […]
Abstract This talk highlights the critical need and urgency for academic communities to advance artificial intelligence (AI) with a focus on value-driven and socially-beneficial LLMs. The presentation is structured in […]
Abstract I will overview our recent results on diffusion generative modelling and how to make inference faster, just in a few steps; also, I will provide some new concepts of […]
Zoom Link: https://hku.zoom.us/j/98499142544?pwd=zvVs3BqWzIzCA071Dqq2rYW7vIAqj7.1 Abstract The advent of GPT-4o highlights the immense potential of Multimodal Large Language Models (MLLMs) with native visual generation capabilities. These unified models offer precise control in […]
Zoom Link: https://hku.zoom.us/j/91953486299?pwd=lEW6N6JKhmAHLoS38VohufbEoJyJtw.1 Abstract This seminar examines how modern image generation models can be redesigned to achieve both high fidelity and high efficiency under flexible inference budgets. I will begin […]
Abstract The speaker aims to provide an update on recent progress by his research team on machine learning for communication networks. If time permits, he will also highlight his work […]
Abstract This seminar provides a systematic showcase of our end-to-end energy-efficient solutions in AI accelerator design, spanning from the foundational compute unit to specialized architectures and large model deployment on […]
Zoom Link: https://hku.zoom.us/j/6983793721?pwd=UjwaYARlhjvhUf7DDp3bMjbJnlhVbr.1 Abstract Structured illumination refers to a class of optical imaging methods in which the sample is illuminated with a controlled spatial light pattern rather than uniform illumination. […]
Abstract Brain health is one of the key societal challenges for the 21st century, and much progress has been made in understanding and treating brain health conditions, aided by growing […]
Abstract In this talk, we will introduce SubLoRA, a rank determination method for Low-Rank Adaptation (LoRA) based on submodular function maximisation. In contrast to prior approaches, such as AdaLoRA, that […]
Abstract Split Federated Learning (SFL) combines computational efficiency with privacy preservation, but existing incentive mechanisms assume uniform cut-layer configurations across clients. This seminar presents a novel incentive mechanism that accounts […]
Abstract Colloidal semiconductor quantum dot nanocrystals (QD NCs) have been shown to be promising materials for electronic and optoelectronic device applications because of their unique size dependent properties and solution […]
*After the seminar, you are also welcome to attend in-person discussions with the speakers from 11:30 am to 12:30 pm in Room 601J. Abstract Solid-state lasers mean laser systems using […]
Abstract Due to the evident climate change and environmental pressures the future power/energy systems will have to operate, sooner rather than later, in a net-zero environment. This will manifest in […]
Abstract The ongoing energy transition is challenging centralised power system paradigms by rapidly integrating distributed energy resources (DERs), which introduce significant supply-demand variability. This variability complicates grid management and necessitates […]
Zoom Link: https://hku.zoom.us/j/92120929746?pwd=aL2f7KSR1uAb9rKfYOyaxpOKa9SBQL.1 Abstract We strengthen the theoretical foundation of universal graph prompt tuning by introducing stricter constraints, demonstrating that adding prompts to all nodes is a necessary condition for […]
Zoom Link: https://hku.zoom.us/j/98761635562?pwd=7QQk1kgMNRmNcaNcVr3bsVi0A2LbZs.1#success Abstract This paper tackles long-tailed learning where tail classes suffer from poor feature generalization due to limited sample diversity. It makes a key observation—finer-grained datasets are less […]