Hanxun Yu

JonnyYu828

·

https://hanxunyu.github.io/

AI & ML interests

Multimodal LLMs, Spatial Intelligence, Embodied AI

Organizations

Papers 7

arxiv:2606.06891

arxiv:2605.15876

arxiv:2601.22674

arxiv:2512.16561

models 2

JonnyYu828/Stream3D-VLM-4B

Image-Text-to-Text • 5B • Updated Jun 8 • 524 • 3

JonnyYu828/DepthVLM-4B

Depth Estimation • 5B • Updated May 22 • 264 • 8

datasets 3

JonnyYu828/Stream3D-Bench

Viewer • Updated Jun 8 • 10k • 53 • 1

JonnyYu828/Stream3D-1M-Dataset

Preview • Updated Jun 8 • 133 • 1

JonnyYu828/DepthVLM-Bench

Preview • Updated May 26 • 205 • 4