🤝 Open to Collab

Kevin Lin

KevinQHLin

·

https://qhlin.me/

AI & ML interests

Vision-Language Model, Video Understanding, Agent

Recent Activity

upvoted a paper 2 days ago

InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter

upvoted a paper 15 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

upvoted a paper 27 days ago

HumanCLAW: Can Vision-Language Models Act Through a Body?

View all activity

Organizations

KevinQHLin 's datasets 2

KevinQHLin/RICO

Preview • Updated Feb 11, 2025 • 24

KevinQHLin/ScreenSpot

Viewer • Updated Jan 1, 2025 • 1.27k • 856 • 1