view article Article Party is over: regularizing ColBERT models to fix efficient ANN methods lightonai • 10 days ago • 23
view reply Congrats! I explored it this morning and it's crazy fast and well-structured. I enjoyed exploring the different benchmarks 🙌
view article Article MTEB Leaderboard: From a slow demo to feature-rich leaderboard Samoed • 14 days ago • 22
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs Paper • 2604.02045 • Published Apr 2 • 38 • 5
A Causal Language Modeling Detour Improves Encoder Continued Pretraining Paper • 2605.12438 • Published May 12 • 7
jina-embeddings-v5-omni Collection Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated May 12 • 36