17 citations · 43 across the 22 of their papers we have counts for
23 papers
What Transfers from a VLM Teacher? Comparing Supervision Signals for Visual Document Retrieval
Saba Sturua, Han Xiao
Visual document retrievers are trained contrastively: each query is matched to one page labelled relevant - the positive - and pushed away from negatives, pages presumed irrelevant…
TV-Regulated OPD: Direction Matters in On-Policy Distillation
Han Xiao, Yifan Niu, Dongyi Liu +2
On-Policy Distillation (OPD) facilitates the transfer of knowledge from domain expert to student in the post-training phase of Large Language Models (LLMs). However, the supervisio…
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards
Alejandro Barón García, Feng Wang, Emilia Garcia Casademont +1
We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It combines the compressed-vision encoder and the 3B mixture-of-experts decoder of D…
omni-macos: On-Device Omni-Modal Search on Apple Silicon
Han Xiao
We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs on the Mac that already holds the files, so…
Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
Hao Wang, Kun Yuan, Wenlin Zhong +4
Open-weight language models from different families exhibit complementary capabilities, motivating their consolidation into a compact student through on-policy distillation (OPD).…
jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation
Christina Nasika, Feng Wang, Antonis Krasakis +1
Listwise rerankers are the discriminative core of agentic retrieval pipelines, yet production deployment demands efficiency, domain robustness, and fluency on semi-structured data…
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
Han Xiao
Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain. We argue the opposite for dense retrieval, since modern smal…
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning
Dongyi Liu, Yifan Niu, Qinwen Wang +2
Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing…
jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
Florian Hönicke, Michael Günther, Andreas Koukounas +3
In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the VLM-style architectur…
Efficient Scaling of LLM Training with Flexible Context Parallelism
Yifan Niu, Han Xiao, Dongyi Liu +2
Scaling long-context capabilities is crucial for Large Language Models (LLMs). However, real-world data contain a large number of sequences with heterogeneous lengths. Existing tra…
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Mohammad Kalim Akram, Saba Sturua, Nastia Havriushenko +4
Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained w…
jina-vlm: Small Multilingual Vision Language Model
Andreas Koukounas, Georgios Mastrapas, Florian Hönicke +3
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…
Efficient Code Embeddings from Code Generation Models
Daria Kryvosheieva, Saba Sturua, Michael Günther +1
jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically…
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-…
ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
Feng Wang, Zesheng Shi, Bo Wang +2
We present ReaderLM-v2, a compact 1.5 billion parameter language model designed for efficient web content extraction. Our model processes documents up to 512K tokens, transforming…
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
Jianlyu Chen, Nan Wang, Chaofan Li +6
Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data,…
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…
jina-embeddings-v3: Multilingual Embeddings With Task LoRA
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram +8
We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tas…
Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
Rohan Jha, Bo Wang, Michael Günther +7
Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attentio…
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
Michael Günther, Isabelle Mohr, Daniel James Williams +2
Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less like…
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
Andreas Koukounas, Georgios Mastrapas, Michael Günther +11
Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These mod…
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
Isabelle Mohr, Markus Krimmel, Saba Sturua +16
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language. These models are capable of process…
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
Michael Günther, Jackmin Ong, Isabelle Mohr +10
Text embedding models have emerged as powerful tools for transforming sentences into fixed-sized feature vectors that encapsulate semantic information. While these models are essen…