SJTU VisionXLab

AI & ML interests

None defined yet.

Recent Activity

Qingyun  authored a paper about 2 months ago

Co-Training Vision Language Models for Remote Sensing Multi-task Learning

Qingyun  authored a paper 4 months ago

Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration

Qingyun  authored a paper 4 months ago

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

View all activity

Papers

Co-Training Vision Language Models for Remote Sensing Multi-task Learning

View all Papers

Team members 6