Jingxuan Kang

PhD Student, University of Illinois Urbana-Champaign

I work on computer vision and machine learning, focusing on cross-modal learning and data-efficient visual understanding. Currently exploring vision-language models and their applications in medical imaging.

Publications Email

About

I'm a PhD student at UIUC working with Prof. [Advisor Name]. My research explores how to make vision models more data-efficient by leveraging language knowledge and cross-modal learning.

Recent work includes vision-language model adaptation, semantic graph-guided learning, and applications to medical imaging (autonomous catheterization). I've published at ICML, ICCV, NeurIPS, and ACM MM.

9
papers
44
citations
5
h-index
9
i10-index

Research

Computer Vision

Vision-language models, cross-modal learning

Cross-Modal Learning

Data-efficient learning, semantic alignment

Medical Imaging

Autonomous catheterization, X-ray analysis

Style Transfer

Image translation, domain adaptation

Publications

2025

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

J Kang, L Cai, S Li, W Ma, B Xie, Z Qin, J Liang

International Conference on Machine Learning (ICML) • 引用: 2

PDF arXiv
2024

Enhancing cross-modal fine-tuning with gradually intermediate modality generation

L Cai, S Li, W Ma, J Kang, B Xie, Z Sun, C Zhu

International Conference on Machine Learning (ICML) • 引用: 2

PDF arXiv
2024

Learning modality knowledge alignment for cross-modality transfer

W Ma, S Li, L Cai, J Kang

International Conference on Machine Learning (ICML) • 引用: 4

PDF arXiv
2024

Translating simulation images to x-ray images via multi-scale semantic matching

J Kang, T Jianu, B Huang, B Bhattarai, N Le, F Coenen, A Nguyen

MICCAI Workshop on Data Engineering in Medical Imaging • 引用: 1

PDF arXiv
2024

Autonomous catheterization with open-source simulator and expert trajectory

T Jianu, B Huang, T Vo, MN Vu, J Kang, H Nguyen, O Omisore, ...

arXiv preprint arXiv:2401.09059 • 引用: 9

PDF arXiv
2023

Borrowing knowledge from pre-trained language model: a new data-efficient visual learning paradigm

W Ma, S Li, JM Zhang, CH Liu, J Kang, Y Wang, G Huang

International Conference on Computer Vision (ICCV) • 引用: 10

PDF Paper
2023

Language semantic graph guided data-efficient learning

W Ma, S Li, L Cai, J Kang

Neural Information Processing Systems (NeurIPS) • 引用: 5

PDF arXiv
2023

Style Transfer Meets Super-Resolution: Advancing Unpaired Infrared-to-Visible Image Translation with Detail Enhancement

J Kang, Y Shen, S Li, Z Yu, S Wang

ACM Multimedia • 引用: 6

PDF Paper
2023

Shape-sensitive loss for catheter and guidewire segmentation

C Kongtongvattana, B Huang, J Kang, H Nguyen, O Olufemi, A Nguyen

International Conference on Robot Intelligence Technology and Applications • 引用: 5

PDF arXiv
View All Publications on Google Scholar

Contact

Email

jk107@illinois.edu

Office

Computer Science Department
University of Illinois at Urbana-Champaign
Urbana-Champaign, IL 61801

Google Scholar

View Profile

Contact Form