Junhyeok Kim

kjunh

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 7 days ago

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

upvoted a paper about 1 month ago

Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding

upvoted a paper 2 months ago

HumanCLAW: Can Vision-Language Models Act Through a Body?

View all activity

Organizations

Papers 2

arxiv:2505.18842

arxiv:2502.14892

models 2

kjunh/v1-7B

Image-Text-to-Text • 8B • Updated Jul 25, 2025 • 16

kjunh/EgoSpeak

Updated Feb 11, 2025

datasets 4

kjunh/v1g

Viewer • Updated Jul 20 • 312k • 403

kjunh/GuideDog

Viewer • Updated Apr 28 • 22.9k • 96 • 4

kjunh/v1g-sample

Viewer • Updated Oct 20, 2025 • 100 • 125

kjunh/EgoSpeak

Updated Feb 26, 2025 • 107 • 1