😁 gogogo

Sean Yu

yushaohan

·

https://yushaohan.github.io/

yushaohan

AI & ML interests

Reinforcement Learning, Visual Generation

Recent Activity

upvoted a paper 8 days ago

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

upvoted a paper 9 days ago

UniWorld-Design: From Pixel Generation to Layer-Native Design

upvoted a paper 9 days ago

AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling

View all activity

Organizations

commented a paper 4 months ago

WorldMark: A Unified Benchmark Suite for Interactive Video World Models

Paper • 2604.21686 • Published Apr 23 • 36 •

New activity in yushaohan/ProGuard-7B 6 months ago

Add model metadata and link to DeepSight paper

#1 opened 6 months ago by

commented a paper 8 months ago

ProGuard: Towards Proactive Multimodal Safeguard

Paper • 2512.23573 • Published Dec 29, 2025 • 6 •