Yudong Jin

krahets

·

AI & ML interests

3D Vision

Recent Activity

new activity 14 minutes ago

AntResearch/4DAnyone:Demo for this model on Spaces

commentedon a paper about 3 hours ago

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

authored a paper about 4 hours ago

Native Video-Action Pretraining for Generalizable Robot Control

View all activity

Organizations

Papers 5

arxiv:2607.08639

arxiv:2606.32036

arxiv:2604.08542

arxiv:2507.13344

models 1

krahets/Diffuman4D

Video-to-Video • 0.8B • Updated Sep 10, 2025 • 45 • 8

datasets 2

krahets/dna_rendering_processed

Viewer • Updated Nov 18, 2025 • 1.04k • 3.48k • 7

krahets/diffuman4d_example

Viewer • Updated Sep 11, 2025 • 2 • 190 • 2