Junjie Fei

FeiElysia's activity

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

liked a model 11 days ago

Vision-CAIR/Tempo-6B

Video-Text-to-Text • Updated 11 days ago • 243 • 2

upvoted a collection 11 days ago

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 11 days ago • 1

liked a Space 14 days ago

Running on Zero

Agents

5

Tempo

🏃

5

Smart Compressors for Long Video Understanding

upvoted 2 papers 14 days ago

Neural Computers

Paper • 2604.06425 • Published 19 days ago • 31

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

Paper • 2604.08120 • Published 17 days ago • 20

authored 5 papers 16 days ago

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Paper • 2305.02677 • Published May 4, 2023 • 1

Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents

Paper • 2411.16740 • Published Nov 23, 2024 • 2

WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation

Paper • 2503.19065 • Published Mar 24, 2025 • 11

Neural Computers

Paper • 2604.06425 • Published 19 days ago • 31

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

Paper • 2604.08120 • Published 17 days ago • 20

submitted a paper to Daily Papers 16 days ago

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

Paper • 2604.08120 • Published 17 days ago • 20

authored a paper over 1 year ago

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

Paper • 2307.16525 • Published Jul 31, 2023 • 1