Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jungha Wang

Jungha Wang

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Vision×1AI×1Robotics×1

Frequent co-authors

Jehun Kang1×
Youngjun Hwang1×
David Hyunchul Shim1×

Research Timeline

2026
DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative inductive transfer between tasks.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.ROEmpiricalRecentJul 17, 2026

DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction

Jehun Kang, Jungha Wang, Youngjun Hwang, David Hyunchul Shim

This paper proposes DPNeXt, a streamlined multi-scale feature fusion decoder for Multi-Task Learning (MTL) in robotics perception systems, improving frozen VFM utilization and mitigating negative indu…

View →