@inproceedings{an-etal-2026-jasper,
title = "Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models",
author = "An, Haining and
Chen, Xingbing and
Lyu, Wenbo and
Zhang, Dun and
Zeng, Ziyang and
Zhao, Zhenxiang and
Song, Rui and
Xu, Hao",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1125/",
pages = "25766--25789",
ISBN = "979-8-89176-459-0",
abstract = "Deploying text embedding models under resource constraints is challenged by the sequence-length-dependent computational cost of self-attention. However, existing sequence-reduction strategies remain predominantly static and offer limited flexibility across inference budgets. We propose Jasper-Flash, an inference-scalable text embedding framework combining Elastic Token Compression (ETC) with Compression-Adaptive Progressive Distillation (CAPD). ETC uses a length threshold and a user-selected compression ratio to adjust sequence length on the fly, enabling flexible latency{--}quality trade-offs within a single model. To mitigate the optimization difficulty introduced by lossy sequence reduction, CAPD integrates heterogeneous multi-teacher distillation with a progressive curriculum over fixed and dynamically sampled compression ratios. We instantiate Jasper-Flash as Jasper-Token-Compression-600M, a bilingual text embedding model. Experiments on MTEB and C-MTEB demonstrate competitive performance across compression ratios and substantial reductions in encoding latency, particularly for longer inputs. The code and model are available at https://huggingface.co/infgrad/Jasper-Token-Compression-600M."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2026-jasper">
<titleInfo>
<title>Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haining</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingbing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenxiang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Deploying text embedding models under resource constraints is challenged by the sequence-length-dependent computational cost of self-attention. However, existing sequence-reduction strategies remain predominantly static and offer limited flexibility across inference budgets. We propose Jasper-Flash, an inference-scalable text embedding framework combining Elastic Token Compression (ETC) with Compression-Adaptive Progressive Distillation (CAPD). ETC uses a length threshold and a user-selected compression ratio to adjust sequence length on the fly, enabling flexible latency–quality trade-offs within a single model. To mitigate the optimization difficulty introduced by lossy sequence reduction, CAPD integrates heterogeneous multi-teacher distillation with a progressive curriculum over fixed and dynamically sampled compression ratios. We instantiate Jasper-Flash as Jasper-Token-Compression-600M, a bilingual text embedding model. Experiments on MTEB and C-MTEB demonstrate competitive performance across compression ratios and substantial reductions in encoding latency, particularly for longer inputs. The code and model are available at https://huggingface.co/infgrad/Jasper-Token-Compression-600M.</abstract>
<identifier type="citekey">an-etal-2026-jasper</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1125/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>25766</start>
<end>25789</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models
%A An, Haining
%A Chen, Xingbing
%A Lyu, Wenbo
%A Zhang, Dun
%A Zeng, Ziyang
%A Zhao, Zhenxiang
%A Song, Rui
%A Xu, Hao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F an-etal-2026-jasper
%X Deploying text embedding models under resource constraints is challenged by the sequence-length-dependent computational cost of self-attention. However, existing sequence-reduction strategies remain predominantly static and offer limited flexibility across inference budgets. We propose Jasper-Flash, an inference-scalable text embedding framework combining Elastic Token Compression (ETC) with Compression-Adaptive Progressive Distillation (CAPD). ETC uses a length threshold and a user-selected compression ratio to adjust sequence length on the fly, enabling flexible latency–quality trade-offs within a single model. To mitigate the optimization difficulty introduced by lossy sequence reduction, CAPD integrates heterogeneous multi-teacher distillation with a progressive curriculum over fixed and dynamically sampled compression ratios. We instantiate Jasper-Flash as Jasper-Token-Compression-600M, a bilingual text embedding model. Experiments on MTEB and C-MTEB demonstrate competitive performance across compression ratios and substantial reductions in encoding latency, particularly for longer inputs. The code and model are available at https://huggingface.co/infgrad/Jasper-Token-Compression-600M.
%U https://aclanthology.org/2026.emnlp-main.1125/
%P 25766-25789
Markdown (Informal)
[Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models](https://aclanthology.org/2026.emnlp-main.1125/) (An et al., EMNLP 2026)
ACL
- Haining An, Xingbing Chen, Wenbo Lyu, Dun Zhang, Ziyang Zeng, Zhenxiang Zhao, Rui Song, and Hao Xu. 2026. Jasper-Flash: Elastic Token Compression and Progressive Distillation for Inference-Scalable Text Embedding Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 25766–25789, Budapest, Hungary. Association for Computational Linguistics.