Patrick (Tsung-Han) Wu

tsunghanwu

·

https://patrickthwu.com/

AI & ML interests

Vision and Language

Recent Activity

upvoted a paper 6 days ago

OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?

authored a paper about 1 month ago

SAM 3: Segment Anything with Concepts

authored a paper about 1 month ago

DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching

View all activity

Organizations

tsunghanwu 's models 7

tsunghanwu/reverse-instruct-1.3m

Updated May 30, 2025

tsunghanwu/reverse_qwen25_vl

Image-Text-to-Text • 4B • Updated May 30, 2025 • 25

tsunghanwu/reverse_llava_v15

Image-Text-to-Text • 7B • Updated May 4, 2025 • 26 • 1

tsunghanwu/reverse_llava_more

8B • Updated Apr 18, 2025 • 16 • 1

tsunghanwu/mirage-llama3.1-8.3B

9B • Updated Oct 18, 2024 • 15 • 1

tsunghanwu/SESAME_minus

Text Generation • Updated Jun 16, 2024 • 261

tsunghanwu/SESAME

Text Generation • Updated Jun 16, 2024 • 302 • 2