23 Apr 2026
Chenqi Presents at ICLR 2026 in Rio de Janeiro
On 23rd April 2026, Chenqi gave an oral presentation at the International Conference on Learning Representations (ICLR) in Rio de Janeiro, Brazil. The event gathers leading academic researchers, industry pioneers, and engineers to discuss foundational methodologies, agentic systems, and transformative AI applications. With its rigorous standards and focus on next-generation architectures, ICLR serves as a premier international venue for presenting research that actively shapes the future of machine learning.
During the conference, Chenqi presented BioX-Bridge, a novel framework designed for unsupervised cross-modal knowledge transfer across biosignals. This innovative work introduces a lightweight "bridge" mechanism that successfully transfers knowledge between models trained on entirely different modalities, crucially without the need for labelled data. The BioX-Bridge approach demonstrates remarkable efficiency by reducing the number of trainable parameters by at least 88%, enabling robust knowledge transfer even in highly resource-constrained environments. Rigorously validated across four distinct biosignal modalities and six diverse transfer directions, this framework offers a highly scalable and adaptable new tool for researchers working at the intersection of AI and biomedical engineering.
