<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-stratprune">
    <titleInfo>
        <title>StratPrune: Cascade Stratum Pruning for Efficient Time Series Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chenghao</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qian</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aniket</namePart>
        <namePart type="family">Mahanti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="given">Xing</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingwei</namePart>
        <namePart type="family">Yi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Fan</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>Multimodal large language models have recently shown strong potential for time series reasoning, where models jointly process textual context and long numerical sequences. However, dense time series representations introduce a large number of tokens, leading to substantial computational and memory overhead during inference. Existing token pruning methods are mainly designed for visual tokens and typically rely on global attention or representation geometry, overlooking the fact that token redundancy varies across layers and modalities. This makes pruning-induced perturbations difficult to control, especially when tokens are pruned across multiple transformer layers. In this paper, we propose StratPrune, a cascade stratum pruning framework for efficient time series reasoning. StratPrune first identifies an early-layer pruning stratum where time series tokens remain less diverse than text tokens, indicating high redundancy suitable for stable pruning. We then derive a hidden-state stability bound that decomposes pruning-induced perturbation into a layer-dependent stability term and a token-level attention saliency term. Guided by this analysis, StratPrune allocates layer-wise pruning budgets according to time series diversity and removes low-saliency time series tokens through a context-aware cascade process. Experiments on 7 tasks show that StratPrune outperforms strong pruning baselines under matched token budgets, achieving up to 30% relative improvement.</abstract>
    <identifier type="citekey">liu-etal-2026-stratprune</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.807/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>18796</start>
            <end>18813</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T StratPrune: Cascade Stratum Pruning for Efficient Time Series Reasoning
%A Liu, Chenghao
%A Liu, Qian
%A Mahanti, Aniket
%A Wang, Alex Xing
%A Yi, Jingwei
%A Fan, Wei
%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 liu-etal-2026-stratprune
%X Multimodal large language models have recently shown strong potential for time series reasoning, where models jointly process textual context and long numerical sequences. However, dense time series representations introduce a large number of tokens, leading to substantial computational and memory overhead during inference. Existing token pruning methods are mainly designed for visual tokens and typically rely on global attention or representation geometry, overlooking the fact that token redundancy varies across layers and modalities. This makes pruning-induced perturbations difficult to control, especially when tokens are pruned across multiple transformer layers. In this paper, we propose StratPrune, a cascade stratum pruning framework for efficient time series reasoning. StratPrune first identifies an early-layer pruning stratum where time series tokens remain less diverse than text tokens, indicating high redundancy suitable for stable pruning. We then derive a hidden-state stability bound that decomposes pruning-induced perturbation into a layer-dependent stability term and a token-level attention saliency term. Guided by this analysis, StratPrune allocates layer-wise pruning budgets according to time series diversity and removes low-saliency time series tokens through a context-aware cascade process. Experiments on 7 tasks show that StratPrune outperforms strong pruning baselines under matched token budgets, achieving up to 30% relative improvement.
%U https://aclanthology.org/2026.emnlp-main.807/
%P 18796-18813

Markdown (Informal)

[StratPrune: Cascade Stratum Pruning for Efficient Time Series Reasoning](https://aclanthology.org/2026.emnlp-main.807/) (Liu et al., EMNLP 2026)

• StratPrune: Cascade Stratum Pruning for Efficient Time Series Reasoning (Liu et al., EMNLP 2026)

ACL

• Chenghao Liu, Qian Liu, Aniket Mahanti, Alex Xing Wang, Jingwei Yi, and Wei Fan. 2026. StratPrune: Cascade Stratum Pruning for Efficient Time Series Reasoning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 18796–18813, Budapest, Hungary. Association for Computational Linguistics.