Jang Hyun (Vincent) Cho

I am a 4th year CS PhD student at UT Austin, advised by Prof. Philipp Krähenbühl. Before I joined UT Austin, I received my Bachelor degree in Computer Science from Cornell University, where I had pleasure working with Prof. Bharath Hariharan and Prof. Kavita Bala.

My current research focus lies in computer vision and machine learning, mainly about object detection, vision-language models, and foundation models. I am particularly interested in scaling up recognition system that readily adapts to various downstream applications.

(Last updated: April. 2024)


Feb 27, 2024 DECOLA has been accepted to CVPR 2024. See you in Seattle!
Sep 18, 2023 I joined NVIDIA AV Research as a research intern.
Mar 5, 2023 PartDistillation has been accepted to CVPR 2023.
Jul 3, 2022 ECM-Loss has been accepted to ECCV 2022 as Oral!
May 23, 2022 I joined FAIR as a research scientist intern.


cubellm teaser

Language-Image Models with 3D Understanding
Jang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue Wang, Xinshuo Weng, Boyi Li, Yurong You, Philipp Krähenbühl, Yan Wang, Marco Pavone
arXiv, 2024

Language-conditioned Detection Transformer
Jang Hyun Cho, Philipp Krähenbühl
CVPR, 2024

PartDistillation: Learning Parts from Instance Segmentation
Jang Hyun Cho, Philipp Krähenbühl, Vignesh Ramanathan
CVPR, 2023

NMS Strikes Back
Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl
arXiv, 2022

Long-tail Detection with Effective Class-Margins
Jang Hyun Cho, Philipp Krähenbühl
European Conference on Computer Vision, ECCV 2022, Tel Aviv, Oct 23-27, 2022 (Oral)

PiCIE: Unsupervised Semantic Segmentation Using Invariance and Equivariance in Clustering
Jang Hyun Cho, Utkarsh Mall, Kavita Bala, and Bharath Hariharan
In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021

On the Efficacy of Knowledge Distillation
Jang Hyun Cho, and Bharath Hariharan
In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019