Ivan Lee

ivnle's activity

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

upvoted a paper 17 days ago

Optical Context Compression Is Just (Bad) Autoencoding

Paper • 2512.03643 • Published 24 days ago • 1

upvoted a collection about 1 year ago

🦙📚 LlamaTales

Collection

From the paper 'Readability ≠ Learnability: Rethinking the Role of Simplicity in Training Small Language Models' (COLM 2025) • 36 items • Updated Aug 8 • 1