arxiv:2509.25190
Haiwen Diao
Paranioar
AI & ML interests
Vision-and-Language, Parameter-efficient Transfer Learning, Multi-modal Large Language Model
Recent Activity
authored
a paper
3 days ago
Visual Jigsaw Post-Training Improves MLLMs
upvoted
a
paper
3 days ago
Visual Jigsaw Post-Training Improves MLLMs
upvoted
a
paper
about 2 months ago
Next Visual Granularity Generation
Organizations
models
0
None public yet
datasets
0
None public yet