junxin zhao

lotusjx's activity

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

upvoted a paper about 5 hours ago

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Paper • 2610.18860 • Published 2 days ago • 78

upvoted a paper 3 months ago

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published Jul 16 • 147

upvoted a collection 4 months ago

LLM2CLIP

Collection

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated Mar 2 • 69

upvoted a paper 5 months ago

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Paper • 2605.23904 • Published May 22 • 268

upvoted a paper 6 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 122

New activity in google/siglip-so400m-patch14-224 over 1 year ago

Why is max_position_embeddings set to only 16 instead of 64?

1

#2 opened over 1 year ago by

lotusjx