Ouyang Ziheng's picture

Ouyang Ziheng

ziheng1234

·

AI & ML interests

None yet

Recent Activity

liked a Space 4 days ago

ziheng1234/ImageCritic

upvoted a paper about 1 month ago

BayesianVLA: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

upvoted a paper 3 months ago

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

View all activity

Organizations

Papers 3

arxiv:2511.20614

arxiv:2511.19990

arxiv:2510.05715

spaces 1

ImageCritic

Official Demo of ImageCritic

models 3

ziheng1234/ImageCritic

Image-to-Image • Updated Dec 3, 2025 • 483 • 5

ziheng1234/fluxdev

Text-to-Image • Updated Nov 27, 2025 • 10

ziheng1234/kontext

Image-to-Image • Updated Aug 17, 2025 • 102

datasets 3

ziheng1234/Critic-10K

Viewer • Updated Dec 3, 2025 • 5.9k • 2.28k • 5

ziheng1234/benchmark_all

Preview • Updated Oct 23, 2025 • 550

ziheng1234/CriticBench

Preview • Updated Oct 18, 2025 • 13