Seminar

Zoom Link  https://hku.zoom.us/j/98470480541?pwd=loAm99UUdaZEqJZNVRfb9d60al7TZe.1 Abstract World models that simulate future states from past observations are increasingly central to video generation and embodied AI. Yet most existing approaches fall short along two […]

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 […]

Zoom Link  https://hku.zoom.us/j/8795454775?omn=92351306157 Abstract Dual‑gate phototransistors enable independent control of carrier accumulation and separation within a single channel, offering high gain, low noise, and tunable responsivity. To start, this seminar […]

  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 […]

Zoom Link  https://hku.zoom.us/meetings/95832932074/invitations?signature=SCg4igomh110T7WUpW6op2xeFgb9WgU92xDTYI2sp8s Abstract Text-to-image generation models have achieved impressive visual quality, yet they largely fail when prompts require reasoning or world knowledge to interpret. Generating an image of "a […]

Zoom Link  https://hku.zoom.us/s/92652052314?pwd=kKKw9mhMHxP8xcObYHFop7VyvAfzh1.1#success Abstract Autoregressive (AR) models have emerged as a powerful paradigm for text-to-image and text-to-video generation, exhibiting exceptional native in-context learning capabilities and scalable performance. However, their real-world […]

Zoom Link  https://hku.zoom.us/j/94632758376 Abstract Additive manufacturing enables customised device fabrication for emerging sensing technologies.  However, printable (opto)electronic devices with sophisticated architectures, including all-printed photodiodes, face challenges in multi-material and multi-layer […]

Zoom Link  https://hku.zoom.us/j/3623268282 Abstract Creating high-quality 3D content requires not only visual realism but also controllability, editability, and structural understanding. This talk focuses on recent progress toward controllable 3D content […]

Zoom Link  https://hku.zoom.us/j/97268323750?pwd=rqO1zHBqvsVUD01hj31lRSV9r6Adhp.1 Abstract Building embodied agents with spatial intelligence remains a fundamental challenge in robotics and embodied AI. Such agents must understand open-vocabulary semantics, maintain long-term spatial memory, and […]

Zoom Link  https://us05web.zoom.us/j/88334748156?pwd=YXWVQUg4FEHYb9nucvsm78fqasXabh.1 Abstract Non-intrusive load monitoring provides appliance-level electricity consumption information from aggregate household measurements, supporting residential energy management without installing sensors on individual appliances. Processing these measurements on […]