MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions
Paper
•
2503.09499
•
Published
•
3
Ling Zhenqing
lingzhq11
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Towards Mitigating Hallucinations in Large Vision-Language Models by
Refining Textual Embeddings
upvoted
a
paper
about 2 months ago
Visual Spatial Tuning
upvoted
a
paper
about 2 months ago
DeepEyesV2: Toward Agentic Multimodal Model
Organizations
authored
a
paper
7 months ago