Jang Hyun (Vincent) Cho

I am a Research Scientist at Meta FAIR Perception. I did my Ph.D. in Computer Science at UT Austin, advised by Prof. Philipp Krähenbühl. Before 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. I have previously worked at Meta and NVIDIA.

My current research interest is broadly in vision-language modeling and multimodal reasoning.

(Last updated: April 2025)



News

Apr 8, 2025 I did my defense!
Jan 22, 2025 Cube-LLM is accepted at ICLR!
Jan 13, 2025 I joined FAIR Perception Team as a Research Scientist!

Publications

ICLR
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
ICLR, 2025
paper website code (coming soon)
CVPR

Language-conditioned Detection Transformer
Jang Hyun Cho, Philipp Krähenbühl
CVPR, 2024
paper website code bibtex
CVPR

PartDistillation: Learning Parts from Instance Segmentation
Jang Hyun Cho, Philipp Krähenbühl, Vignesh Ramanathan
CVPR, 2023
paper website code bibtex
arXiv

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

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)
paper code bibtex
CVPR

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
paper website code bibtex
ICCV

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
paper bibtex