Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
These models improve search accuracy by capturing multiple semantic meanings per word, helping systems better match user intent with relevant results.
Get smart on it
Sentence Transformers version 6.0 introduces a new model type called MultiVectorEncoder for multi-vector embedding models, which keep one vector per token instead of compressing entire texts into a single vector. Multi-vector models defer the interaction between query and document until scoring time using the MaxSim operator, which compares every query token against every document token to find the best matches. This approach preserves token-level matching information and performs better on queries requiring specific pieces of documents or multiple requirements at once, particularly on out-of-domain data, but the tradeoff is a substantially larger index size since one vector per token generates many more vectors than traditional single-vector models.
Related news
The Powerful Chinese AI Model Experts Warned About Is Here
Z.ai’s latest AI model release could help companies secure their systems—or find its way into the hands of hackers.
ByteDance Seed and Tsinghua AIR Introduces CUDA Agent: A Large-Scale Agentic RL System for CUDA Kernel Generation
ByteDance Seed and Tsinghua AIR have released CUDA Agent, an agentic reinforcement learning system that trains a large language model to write GPU kernels that beat a compiler. The gap it targets is narrow but stubborn: frontier models already produce correct CUDA, they just produce slow CUDA. On KernelBench, the base model Seed1.6 passes 74.0% of tasks yet outruns torch.compile on only 27.2% of them, at a 0.69× geometric-mean speedup which means its kernels are, on average, slower than what th
