Wonseok Choi

Wonseok2's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 12 months ago

Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

Paper • 2508.12466 • Published Aug 17, 2025 • 9

upvoted an article almost 2 years ago

view article

Article

Key Insights into the Law of Vision Representations in MLLMs

• 

Borise

•

Sep 2, 2024

• 20