↓Skip to main content
Minkyoung Cho

Minkyoung Cho

Ph.D. Student in CSE at the University of Michigan

Google Scholar icon CV image/svg+xml CV CV

I am a third-year Ph.D. student, fortunate to be advised by Prof. Z. Morley Mao.

My primary research interests lie in multi-modal, efficient AI, and robust AI.
I’m particularly passionate about understanding what makes multi-modal models unique—especially through the lens of interpretability—by focusing on how to effectively and efficiently reconcile different modalities/agents. I also find great fulfillment in enhancing the efficiency & robustness of these models 😃!

News

CrowdMap Accepted to CVPRW'25

We introduce the global vectorized HD map construction task in a collaborative setting among multiple AV agents. See how CrowdMap mitigates redundancy and misalignment in multi-agent HD map fusion — stay tuned for our full paper!

Internship at NVIDIA: Round 2!

Thrilled to return to the NVIDIA Metropolis team, this time diving into Generative AI research!

Cocoon Accepted to ICLR'25

Cocoon is a new object- and feature-level uncertainty-aware multimodal fusion framework designed for 3D OD tasks. See how we achieve uncertainty quantification and comparison for heterogeneous representations!

Our Paper Accepted to ACM CSCS'24

This survey paper on AV security and safety has been developed in collaboration with the AV reading group at UMich. Hope it will serve as vital ammunition for practitioners in the field.

Start Internship at NVIDIA

Will be working as a Deep Learning Software Intern at NVIDIA Metropolis team! See you in Santa Clara :D