Seminar

Zoom Link  https://hku.zoom.us/j/94833409754?pwd=ER6VaveQbdEzOQzhuFKThpSdRusUDs.1 Abstract Consistent 3D geometry estimation from streaming RGB input is crucial for real-world applications such as autonomous driving, embodied AI, and large-scale reconstruction. While modern monocular geometry foundation models achieve strong single-image accuracy, they exhibit severe temporal inconsistency on continuous input, notably dominated by scale–shift drifting. Through targeted empirical analysis, we trace […]

Zoom Link  https://hku.zoom.us/j/94017530661 Abstract There are numerous studies focusing on the crystallization dynamics of perovskite materials. However, the change of precursor properties which can also significantly affect crystallization behavior, is always ignored. In this seminar, we establish a comprehensive understanding of the relationship between A-site cations content and zeta potential of precursor, revealing its influence […]

Zoom Link  https://hku.zoom.us/j/9995553636?omn=96185323037 Abstract This seminar presents robust multivariate autoregressive (MVAR) model estimation under impulsive noise, with a focus on extending bias-compensated instrumental-variable methods to contaminated multichannel observations. MVAR models are widely used in time-series prediction, system identification, biomedical signal analysis, and sensor-array processing. However, conventional estimators can suffer from systematic bias under correlated measurement […]

  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 explore how internal understanding of LLMs can be translated into practical interventions for better capability, efficiency, and controllability. I begin with actionable mechanistic interpretability, introducing […]

Zoom Link  https://hku.zoom.us/j/9021481973?omn=94827890905 Abstract Mutual information has long served as a principled measure of statistical dependence, but computing it from empirical samples is notoriously difficult: neural estimators rely on costly gradient-based optimization for every new dataset, which limits their use inside real-time and large-scale pipelines. This talk presents a framework that pretrains a neural estimator […]