ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model
Paper
•
2510.24285
•
Published
•
3
Zhexuan Zhou
Zhexuanzhou02
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
Organizations
None yet
upvoted
2
papers
2 days ago