Two sub-1B multilingual embeddings with best-in-class performance, available on Elastic Inference Service, Llama.cpp and MLX.

Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained with single- or multi-stage processes using contrastive loss functions. We introduce a novel training regimen that combines model distillation techniques with task-specific contrastive loss to produce compact, high-performance embedding models. Our findings suggest that this approach is more effective for training small models than purely contrastive or distillation-based training paradigms alone. Benchmark scores for the resulting models, jina-embeddings-v5-text-small and jina-embeddings-v5-text-nano, exceed or match the state-of-the-art for models of similar size. jina-embeddings-v5-text models additionally support long texts (up to 32k tokens) in many languages, and generate embeddings that remain robust under truncation and binary quantization. Model weights are publicly available, hopefully inspiring further advances in embedding model development.

We frame embedding inversion as conditional masked diffusion, recovering all tokens in parallel through iterative denoising rather than sequential autoregressive generation. A masked diffusion language model is conditioned on the target embedding via adaptive layer normalization, requiring only 8 forward passes through a 78M parameter model with no access to the target encoder. On 32-token sequences across three embedding models, the method achieves 81.3% token accuracy and 0.87 cosine similarity.

We present a compression method for unit-norm embeddings that achieves 1.5x compression, 25% better than the best prior lossless method. The method exploits that spherical coordinates of high-dimensional unit vectors concentrate around pi/2, causing IEEE 754 exponents to collapse to a single value and high-order mantissa bits to become predictable, enabling entropy coding of both. Reconstruction error is below 1e-7, under float32 machine epsilon. Evaluation across 26 configurations spanning text, image, and multi-vector embeddings confirms consistent improvement. The method requires no training.

Vision encoders have remained comparatively small while language models scaled from billions to hundreds of billions of parameters. This survey analyzes vision encoders across 70+ vision-language models from 2023–2025 and finds that training methodology matters more than encoder size: improvements in loss functions, data curation, and feature objectives yield larger gains than scaling by an order of magnitude. Native resolution handling improves document understanding, and multi-encoder fusion captures complementary features no single encoder provides. We organize encoders into contrastive, self-supervised, and LLM-aligned families, providing a taxonomy and practical selection guidance for encoder design and deployment.

New 2B vision language model achieves SOTA on multilingual VQA, no catastrophic forgetting on text-only tasks.

We present jina-vlm, a 2.4B parameter vision-language model that achieves state-of-the-art multilingual visual question answering among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language backbone through an attention-pooling connector that enables token-efficient processing of arbitrary-resolution images. Across standard VQA benchmarks and multilingual evaluations, jina-vlm achieves leading results while preserving competitive text-only performance. Model weights and code are publicly released.

New 0.6B-parameter listwise reranker that considers the query and all candidate documents in a single context window.

jina-reranker-v3 is a 0.6B parameter multilingual document reranker that introduces a novel last but not late interaction. Unlike late interaction models such as ColBERT that perform separate encoding followed by multi-vector matching, our approach conducts causal self-attention between query and documents within the same context window, enabling rich cross-document interactions before extracting contextual embeddings from the last token of each document. This compact architecture achieves state-of-the-art BEIR performance with 61.94 nDCG@10 while being significant smaller than generative listwise rerankers.

Embedding models aren't the most glamorous aspect of the AI industry, but image generators and chatbots couldn't exist without them.