Open to Collab

3 11 2

Sean Yu

yushaohan

https://yushaohan.github.io/

yushaohan

AI & ML interests

None yet

Recent Activity

upvoted a paper about 19 hours ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

commentedon a paper 4 days ago

WorldMark: A Unified Benchmark Suite for Interactive Video World Models

upvoted a paper 9 days ago

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

View all activity

Organizations

Collections 1

Papers 2

arxiv:2512.23573

arxiv:2511.15169

models 2

yushaohan/ProGuard-3B

Image-Text-to-Text • 4B • Updated Feb 15 • 8

yushaohan/ProGuard-7B

Image-Text-to-Text • 8B • Updated Feb 15 • 27

datasets 1

yushaohan/ProGuard-data

Viewer • Updated Jan 12 • 87k • 22

Sean Yu

AI & ML interests

Recent Activity

Organizations

Collections 1

yushaohan/ProGuard-3B

yushaohan/ProGuard-7B

yushaohan/ProGuard-data

ProGuard: Towards Proactive Multimodal Safeguard

yushaohan/ProGuard-3B

yushaohan/ProGuard-7B

yushaohan/ProGuard-data

ProGuard: Towards Proactive Multimodal Safeguard

Papers 2

models 2

yushaohan/ProGuard-3B

yushaohan/ProGuard-7B

datasets 1

yushaohan/ProGuard-data

Sean Yu

AI & ML interests

Recent Activity

Organizations

Collections 1

Papers 2

models 2 Sort: Recently updated

datasets 1

models 2