Michael Günther

michael-g-u.bsky.social

18 February 2025 14:37

I applied LLMs for query expansion and we wrote this article: It sees to work out-of-the-box and generally boost the performance of embedding models. However, it requires more latency. Would be interesting to see more about this. 📃: jina.ai/news/query-e... 🛠️: github.com/jina-ai/llm-...

Michael Günther

michael-g-u.bsky.social

16 December 2024 16:23

Our submission to ECIR 2025 on jina-embeddings-v3 has been accepted! 🎉 At the ECIR Industry Day my colleague @str-saba.bsky.social presents how we train the latest version of our text embedding model. More details on ECIR: ecir2025.eu More details about the model: arxiv.org/abs/2409.10173

Saahil Ognawala

saahilognawala.bsky.social

03 December 2024 16:47

@bowang0911.bsky.social showed me this cool paper that I'd never read before, about Masked Autoencoder (MAE) for images. The idea: an image encoder encodes non-masked patches, followed by a decoder using the non-masked and masked embeddings to regenerate the original image arxiv.org/abs/2111.06377

Saahil Ognawala

saahilognawala.bsky.social

03 December 2024 16:47

Got a bit into a rabbit hole of image modelling, after talking to a colleague last week. While Jina CLIP models employ EVA-02 as image tower, I wanted to know if there's an equivalent to masked "patch prediction" for images, like MLM in pre-trained text models arxiv.org/abs/2303.11331 (1/n)

Tom Aarsen

tomaarsen.com

27 November 2024 15:36

I'm looking for an intern to introduce Sparse Embedding models to Sentence Transformers! If you're passionate about open source, interested in helping practitioners use your tools, and enjoy embedders/retrievers/rerankers, then I'd love to hear from you! Links with details and to apply in 🧵