Junjie Fei

FeiElysia's activity

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

upvoted 2 collections 1 day ago

LongVU

Collection

8 items • Updated 1 day ago • 1

Tempo

Collection

Official Tempo-6B collection: A query-aware framework solving the mismatch between massive video streams and bounded LLM context windows. • 6 items • Updated 1 day ago • 1

upvoted 2 papers 4 days ago

Neural Computers

Paper • 2604.06425 • Published 9 days ago • 29

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Paper • 2604.08120 • Published 7 days ago • 20