Jixuan Ying

Jixuan Ying

Tsinghua undergraduate and SenseTime research intern working on interleaved multimodal reasoning and efficient visual architectures.

InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation

Published in International Journal of Computer Vision (IJCV), 2025

This work proposes InfoPro, a locally supervised deep learning framework that maximizes information propagation to improve information flow and feature expression, leading to stronger generalization and training efficiency across multiple mainstream datasets.

My contribution focused on independently conducting multiple experiments and systematically validating the improvements in generalization and training efficiency.

Recommended citation: Y. Wang*, Z. Ni*, Y. Pu, C. Zhou, Jixuan Ying, S. Song, G. Huang. "InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation." IJCV 2025.
Download Paper