In this talk, we delve into two pivotal subjects. The   first topic revolves around the development of hybrid graph models tailored   to the complexities of multi-modal data. We present a novel semi-supervised   hypergraph learning framework, specifically designed for diagnostic purposes.   Our approach adopts a hybrid perspective, where we introduce a new   methodology centered on a dual embedding strategy and a semi-explicit flow.   To illustrate the efficacy of our proposed model, we employ it within the   realm of Alzheimer's disease diagnosis, demonstrating its capacity to uncover   latent relationships within intricate multi-modal data.

Transitioning seamlessly to the   second subject, we delve into implicit neural representations. We introduce   an innovative function designed to harness the strengths of Strong Spatial   and Frequency attributes, marking a departure from conventional methods.   Remarkably, our novel technique showcases exceptional enhancements in   performance across a diverse array of downstream tasks, notably encompassing   CT reconstruction and denoising applications. Through rigorous   experimentation, we elucidate the advantages enabled by our approach.

Concluding our discourse, we shed   light on emerging trends within Diffusion models, reflecting on their   evolving role and potential. By amalgamating insights from hybrid graph   models, implicit neural representations, and diffusion modeling, this talk   serves as a comprehensive exploration of transformative techniques and trends   in the field.

Biography:

She is a Senior Research Associate at the Department   of Applied Mathematics and Theoretical Physics (DAMTP), University of   Cambridge. Her work focuses at the confluence of computational mathematics, computer   vision, and machine learning, where she addresses complex real-world problems   on a large scale.

Her expertise lies in developing   large-scale mathematical and machine learning models with minimal or even no   supervision. This has led to her being sought after for consultations by   various centers and companies.

She has large experience in   organising scientific meetings including BMVC2022 & BMVC 2023   (co-organiser), MIUA22 (co-organiser),  MICCAI Tutorials, ACCV   Tutorials, IGARSS Tutorials,  and GeoMedIA Workshop.

She serves as a current SIAM   SIAG/IS Officer.

For more info: https://angelicaiaviles.wordpress.com/