<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jumakhan-etal-2026-ajman">
    <titleInfo>
        <title>Ajman University at SemEval-2026 Task 2: Overcoming Scale Collapse in Temporal Emotion Modeling via Residual Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haseebullah</namePart>
        <namePart type="family">Jumakhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soud</namePart>
        <namePart type="family">Assad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Seyed</namePart>
        <namePart type="family">Abdullah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mahmoud</namePart>
        <namePart type="family">Al-Ayyoub</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Kochmar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debanjan</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mamoru</namePart>
            <namePart type="family">Komachi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-414-9</identifier>
    </relatedItem>
    <abstract>Ajman University Team develops a set of specialized architectures for longitudinal affective forecasting for SemEval-2026 Task 2. We establish a baseline for our performance with a standard transformer model that sets our performance floor in Subtask 1 (ranked 18). In Subtask 2A (ranked 7) and Subtask 2B (ranked 8), our main contribution is to address the problem of scale collapse. To address the scale collapse, we use a novel “bifurcated leviathan” architecture to combine residual learning with target scaling. Our additional contribution is that we counteract the effects of regression to the mean by using optimized covariance via specialized objective functions (CCC and Huber). We use these objective functions while enforcing strict user level data splits. Finally, we show empirically that standard gradient stabilization methods decrease zero shot cross subject generalization, even when they optimize intra subject memorization.</abstract>
    <identifier type="citekey">jumakhan-etal-2026-ajman</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.66/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>457</start>
            <end>462</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Ajman University at SemEval-2026 Task 2: Overcoming Scale Collapse in Temporal Emotion Modeling via Residual Learning
%A Jumakhan, Haseebullah
%A Assad, Soud
%A Abdullah, Seyed
%A Al-Ayyoub, Mahmoud
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F jumakhan-etal-2026-ajman
%X Ajman University Team develops a set of specialized architectures for longitudinal affective forecasting for SemEval-2026 Task 2. We establish a baseline for our performance with a standard transformer model that sets our performance floor in Subtask 1 (ranked 18). In Subtask 2A (ranked 7) and Subtask 2B (ranked 8), our main contribution is to address the problem of scale collapse. To address the scale collapse, we use a novel “bifurcated leviathan” architecture to combine residual learning with target scaling. Our additional contribution is that we counteract the effects of regression to the mean by using optimized covariance via specialized objective functions (CCC and Huber). We use these objective functions while enforcing strict user level data splits. Finally, we show empirically that standard gradient stabilization methods decrease zero shot cross subject generalization, even when they optimize intra subject memorization.
%U https://aclanthology.org/2026.semeval-1.66/
%P 457-462

Markdown (Informal)

[Ajman University at SemEval-2026 Task 2: Overcoming Scale Collapse in Temporal Emotion Modeling via Residual Learning](https://aclanthology.org/2026.semeval-1.66/) (Jumakhan et al., SemEval 2026)

• Ajman University at SemEval-2026 Task 2: Overcoming Scale Collapse in Temporal Emotion Modeling via Residual Learning (Jumakhan et al., SemEval 2026)

ACL

• Haseebullah Jumakhan, Soud Assad, Seyed Abdullah, and Mahmoud Al-Ayyoub. 2026. Ajman University at SemEval-2026 Task 2: Overcoming Scale Collapse in Temporal Emotion Modeling via Residual Learning. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 457–462, San Diego, California, USA. Association for Computational Linguistics.