5 papers
jina-vlm: Small Multilingual Vision Language Model
Andreas Koukounas, Georgios Mastrapas, Florian Hönicke +5
We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples…
Diffusion-Pretrained Dense and Contextual Embeddings
Sedigheh Eslami, Maksim Gaiduk, Markus Krimmel +3
In this report, we introduce pplx-embed, a family of multilingual embedding models that employ multi-stage contrastive learning on a diffusion-pretrained language model backbone fo…
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
Michael Günther, Saba Sturua, Mohammad Kalim Akram +8
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-…
jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
Andreas Koukounas, Georgios Mastrapas, Sedigheh Eslami +7
Contrastive Language-Image Pretraining (CLIP) has been widely used for crossmodal information retrieval and multimodal understanding tasks. However, CLIP models are mainly optimize…
ELSA: Evaluating Localization of Social Activities in Urban Streets using Open-Vocabulary Detection
Maryam Hosseini, Marco Cipriano, Sedigheh Eslami +4
Existing Open Vocabulary Detection (OVD) models exhibit a number of challenges. They often struggle with semantic consistency across diverse inputs, and are often sensitive to slig…