You Li's picture

You Li

Michael4933

·

Michael4933

AI & ML interests

NLP, Multi-modal LLM

Recent Activity

upvoted a paper 3 days ago

VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

upvoted a paper 3 days ago

Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

upvoted a paper 13 days ago

Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning

View all activity

Organizations

None yet

Papers 2

arxiv:2501.05767

arxiv:2405.10936

spaces 1

Migician

Demo for Multi-image Grounding model: Migician

models 3

Michael4933/CapImagine-7B

849k • Updated Feb 25 • 8

Michael4933/Monet-7B-stage1

Updated Dec 23, 2025

Michael4933/Migician

Image-Text-to-Text • 8B • Updated May 21, 2025 • 28 • 1

datasets 3

Michael4933/CapImagine-Data

Preview • Updated Feb 25 • 23

Michael4933/MIG-Bench

Viewer • Updated Feb 22, 2025 • 5.89k • 75 • 1

Michael4933/MGrounding-630k

Updated Feb 22, 2025 • 403 • 2