Hexiang Hu's picture

4 4 4

Hexiang Hu

hexianghu

·

https://www.hexianghu.com/

AI & ML interests

Multimodal learning: Vision, Language, etc.

Recent Activity

authored a paper 22 days ago

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

new activity about 2 months ago

Spawning/PD12M:Is it possible to get metadata of the images?

new activity about 2 months ago

Spawning/PD12M:Is it possible to get metadata of the images?

View all activity

Organizations

Papers 16

arxiv:2501.09732

arxiv:2410.10563

arxiv:2408.07009

arxiv:2406.13121

models

None public yet

datasets

None public yet