Haolin Wang's picture

1 9

Haolin Wang

howlin

·

https://howlin-wang.github.io/

AI & ML interests

multimodal generation, unified vision model

Recent Activity

updated a model 13 days ago

howlin/SVG

liked a dataset 16 days ago

WisonZws/RealisVideo-4K

published a model 19 days ago

howlin/SVG

View all activity

Organizations

None yet

authored 3 papers about 2 months ago

DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation

Paper • 2409.03755 • Published Sep 5, 2024 • 4

InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

Paper • 2504.15513 • Published Apr 22

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17 • 48