Faces of Research” series by PostGenAI@Paris

Our Faces of Research series continues with a spotlight on Hudie SUN, whose research explores how artificial intelligence can transform electrospinning-based nanofibre fabrication at the intersection of materials science and AI.

Understanding and Optimising Electrospinning

Electrospinning is a powerful technique used to produce versatile nanofibres with applications in areas such as biomedicine, smart textiles, filtration, and energy storage.

Despite its potential, the process remains difficult to control. Numerous experimental parameters — including voltage, solution viscosity, flow rate, humidity, and temperature — interact simultaneously and strongly influence the final properties of the fibres. As a result, optimisation often relies on costly and time-consuming trial-and-error experimentation.

Under the supervision of Florian De Vuyst and Timothée Baudequin, Hudie SUN is developing an innovative solution to address this challenge.

An AI-Driven Inverse Design Framework

Hudie’s research focuses on building an AI-driven inverse design framework capable of directly identifying optimal electrospinning parameters based on:

• the desired properties of the fibres;
• the environmental fabrication conditions.

Rather than manually testing countless configurations, the framework aims to predict the best experimental settings needed to achieve targeted material characteristics.

Large Vision Models and Diffusion Models for Material Design

At the core of this work is the integration of advanced generative AI technologies, including:

• Large Vision Models (LVMs);
• Diffusion Models.

The objective is to create a bidirectional and generative framework that can both optimise fabrication processes and support the design of new materials with tailored properties.

By combining AI with materials science, this research opens promising perspectives for accelerating experimentation, improving reproducibility, and reducing development costs in advanced manufacturing.

Bridging Experimental Complexity and Material Outcomes

As Hudie SUN explains:

“The goal is to bridge the gap between complex experimental settings and desired material outcomes using the power of generative AI.”

Through this ambitious research, Hudie SUN is contributing to a new generation of intelligent tools for advanced material fabrication.