The Flow has not summarised this story yet — read it at Hugging Face Blog.
We are excited to announce a new embedding model which is significantly more capable, cost effective, and simpler to use.
arXiv:2608.21249v1 Announce Type: new Abstract: While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate t...
arXiv:2605.10073v3 Announce Type: replace Abstract: Pre-trained language models advance patent classification and retrieval by encoding claims as flat token sequences, but they overlook the dependenc...