xiaoxiaoshadiao

xiaoxiaoshadiao's activity

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

upvoted a paper 9 days ago

EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval

Paper • 2610.11553 • Published 15 days ago • 3

upvoted a collection 2 months ago

EVIE — Visual Document Retrieval

Collection

Multilingual visual document retrieval with native 128-dimensional multi-vector token embeddings. Rank #1 on ViDoRe V3 and on ViDoRe V1+V2. • 3 items • Updated Sep 7 • 1

upvoted a paper 3 months ago

Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing

Paper • 2606.03565 • Published Jun 14 • 5