# Jasper-Token-Compression-600M Technical Report

arXiv: https://arxiv.org/abs/2511.14405 · HTML: https://mlsanity.com/paper/2511.14405/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2025.

## Built on by (most cited first, 7 of 7)

- [jina-embeddings-v5-text: Task-Targeted Embedding Distillation](https://mlsanity.com/paper/2602.15547/) (2026)
- [STRABLE: Benchmarking Tabular Machine Learning with Strings](https://mlsanity.com/paper/2605.12292/) (2026)
- [TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding](https://mlsanity.com/paper/2605.04962/) (2026)
- [Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG](https://mlsanity.com/paper/2606.28352/) (2026)
- [Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers](https://mlsanity.com/paper/2608.08809/) (2026)
- [UK-PRBENCH: A Paragraph-Level Precedent Retrieval Benchmark for United Kingdom Case Law](https://mlsanity.com/paper/2609.24613/) (2026)
- [TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings](https://mlsanity.com/paper/2610.17065/) (2026)

## Abstract (arXiv)

This technical report presents the training methodology and evaluation results of the open-source Jasper-Token-Compression-600M model, released in November 2025. Building on previous distillation-based recipes from the English Stella and Jasper models, we successfully extend this approach to a bilingual (English and Chinese) domain, further enhancing model performance through the incorporation of contrastive learning. A key innovation of our model is the introduction of a one-dimensional convolution-based token compression module. We dynamically adjust the compression rate during training, enabling the model to learn more robust and efficient compressed text representations. By combining knowledge distillation with token compression techniques, we achieve significant improvements in both embedding quality and inference efficiency. Our model performs with higher efficiency than a traditional 0.6B model while achieving performance comparable to that of an 8B model. For more information on the model release, visit: https://huggingface.co/infgrad/Jasper-Token-Compression-600M.