-
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 29 -
MaxyLee/DeepPerception
Image-Text-to-Text • Updated • 30 • 2 -
MaxyLee/KVG-Bench
Viewer • Updated • 1.34k • 102 -
MaxyLee/DeepPerception-FGVR
Image-Text-to-Text • Updated • 30
Xinyu Ma
MaxyLee
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 5 hours ago
InternVL3: Exploring Advanced Training and Test-Time Recipes for
Open-Source Multimodal Models
upvoted
a
collection
19 days ago
Qwen2.5-VL
new activity
27 days ago
MaxyLee/KVG:Update dataset card: add link to paper, change task category
Organizations
None yet
