Qian Yang

QianYangMILA

·

AI & ML interests

None yet

Recent Activity

liked a dataset 2 days ago

QianYangMILA/vdrop-crossview-8k

authored a paper 3 days ago

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

authored a paper 3 days ago

Discovering Failure Modes in Vision-Language Models using RL

View all activity

Organizations

None yet

Papers 5

arxiv:2605.27310

arxiv:2604.04733

arxiv:2412.04616

arxiv:2405.00253

models 0

None public yet

datasets 1

QianYangMILA/vdrop-crossview-8k

Viewer • Updated 7 days ago • 8.98k • 379 • 2