MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Paper
•
2502.17422
•
Published
•
7
•
2
jiarui zhang
jrzhang
AI & ML interests
Natural Language Processing, Commonsense Reasoning
Recent Activity
upvoted
a
paper
8 days ago
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
upvoted
a
paper
13 days ago
Tina: Tiny Reasoning Models via LoRA
updated
a dataset
28 days ago
jrzhang/TextVQA_GT_bbox
Organizations
jrzhang's activity
commented
a
paper
2 months ago