Deyu Meng

Also known as 孟德宇, De-Yu MENG, De-Yu Meng, De-yu Meng, Meng De Yu

Deyu Meng is a machine-learning researcher whose work spans self-paced learning, image denoising and continual learning. He earned B.Sc., M.Sc. and Ph.D. degrees at Xi’an Jiaotong University, taught there, and completed postdoctoral work at The Chinese University of Hong Kong and a sabbatical at Carnegie Mellon. He coauthored Self-Paced Curriculum Learning, DnCNN and the 2024 ICLR honorable-mention paper Meta Continual Learning Revisited. As of October 2026, he is a professor at Xi’an Jiaotong University and a Distinguished Guest Professor in the Department of Engineering Science at Macau University of Science and Technology.

Now at: Xi'an Jiaotong University and Macau University of Science and Technology
Works: 519
Citations: 34,453
h-index: 80
Badges: Rising
Wayfarer
Loyal

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

2001–2008

Three degrees at Xi’an Jiaotong

He earns B.Sc., M.Sc. and Ph.D. degrees from Xi’an Jiaotong University in 2001, 2004 and 2008, respectively.
2008–2009

Early academic appointments

He joins Xi’an Jiaotong University as an assistant professor in October 2008. From January to September 2009, he is a postdoctoral fellow at The Chinese University of Hong Kong.
2012–2014

A Carnegie Mellon sabbatical

He spends a two-year sabbatical at Carnegie Mellon University from 2012 to 2014.
2015–2016

Self-paced learning and DnCNN

In 2015, he coauthors Self-Paced Curriculum Learning, which proposes SPCL to combine prior knowledge with learning progress. In 2016, he coauthors a DnCNN preprint for image denoising; the model uses residual learning and batch normalization to speed training and improve denoising performance.
Since 2017

Professor at Xi’an Jiaotong

At Xi’an Jiaotong University, he becomes a professor in January 2017.
2022–2026

Changjiang Scholar distinction

He holds the Ministry of Education’s Changjiang Scholar Distinguished Professor title for 2022–2026.
2024

An ICLR honorable mention

In 2024, he coauthors Meta Continual Learning Revisited, which proposes Variance Reduced Meta-CL to achieve timely and accurate online Hessian approximation; ICLR gives the paper an honorable mention.
Since 2019

Professor at XJTU and MUST

He is a professor at Xi’an Jiaotong University and a Distinguished Guest Professor in the Department of Engineering Science at Macau University of Science and Technology.