Seminar

Name: RPG Seminar – From Understanding to Intervention: Interpretability-Guided Methods for Improving Large Language Models
Start: 2026-05-19T16:00:00+08:00
End: 2026-05-19T17:00:00+08:00
Location: Room CB-603, 6/F, Chow Yei Ching Building, The University of Hong Kong

May 2026
RPG Seminar – Day–Night Mechanism-Aware Causal Modeling for Wind Power Forecasting: A Physics-Guided NLSEM Framework

May 8 @ 4:00 pm - 5:00 pm

Zoom Link https://hku.zoom.us/j/95263844640 Abstract Wind power forecasting remains highly challenging due to the strong nonlinearity of atmospheric dynamics,pronounced diurnal regime differences, and substantial uncertainties in multi-source meteorological data. Conventional black-box […]
RPG Seminar – Towards Controllable and Cinematic Visual Content Generation

May 13 @ 10:00 am - 11:00 am

Zoom Link https://hku.zoom.us/j/96029601263 Abstract This seminar presents novel solutions to bridge the gap between creative intent and automated visual synthesis. We first address the challenge of compositional alignment in text-to-image […]
RPG Seminar – HIMSA: A Heterogeneous In-Memory Computing and Searching Architecture for Efficient Attention-Based Models

May 14 @ 10:30 am - 11:30 am

Zoom Link https://hku.zoom.us/j/99174148480?pwd=duVxaYZOJDT6MWxDh4OKOMmyo12A7A.1 Abstract The Transformer architecture, the foundation for modern large language models (LLMs), has revolutionized natural language processing and other AI domains. However, its significant computational and memory […]
RPG Seminar – Cooperative Edge AI: From Event-triggered Inference to Efficient Model Downloading

May 14 @ 1:30 pm - 2:30 pm

Zoom Link http://hku.zoom.us/j/7074144117?omn=95813783034 Abstract Cooperative edge AI enables edge devices and edge servers to collaboratively execute intelligent tasks under limited computation, storage, energy, and communication resources. In this talk, we […]
RPG Seminar – From Understanding to Intervention: Interpretability-Guided Methods for Improving Large Language Models

May 19 @ 4:00 pm - 5:00 pm

Room CB-603, 6/F, Chow Yei Ching Building, The University of Hong Kong

Abstract Large language models have achieved impressive performance, but improving them efficiently and reliably requires more than scaling alone. In this talk, I present a series of works that […]

May 2026