<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-long">
    <titleInfo>
        <title>Long-to-Short Video Evidence Reasoning for Grounded Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kaiyan</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junbin</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xun</namePart>
        <namePart type="family">Yang</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>We present LOVER, a \underlineLong to sh\underlineOrt \underlineVideo \underlineEvidence \underlineReinforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) Long-to-short Video Evidence Curriculum Learning, which organizes RL training according to evidence duration and progressively adapts the model from long-range grounding to short-term reasoning; (2) GQA Rewards, which underscore the benefit of IoP reward over IoU for evidence spotting rather than strict temporal span overlap; (3) Adaptive Timestamp Rendering, which adaptively renders timestamps onto video frames using background-aware position and color selection to enhance temporal observability. The three designs are model-agnostic and reciprocal. They effectively improve QA, grounding, and grounded QA performance over different backbones. Notably, LOVER built on Time-R1 achieves new state-of-the-art (SOTA) results among open-source models on popular GQA benchmarks: NExT-GQA and ReXTime. Comprehensive ablation studies further validate the effectiveness of our three innovative components.</abstract>
    <identifier type="citekey">chen-etal-2026-long</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.253/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>5752</start>
            <end>5766</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Long-to-Short Video Evidence Reasoning for Grounded Question Answering
%A Chen, Kaiyan
%A Xiao, Junbin
%A Yang, Xun
%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 chen-etal-2026-long
%X We present LOVER, a \underlineLong to sh\underlineOrt \underlineVideo \underlineEvidence \underlineReinforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) Long-to-short Video Evidence Curriculum Learning, which organizes RL training according to evidence duration and progressively adapts the model from long-range grounding to short-term reasoning; (2) GQA Rewards, which underscore the benefit of IoP reward over IoU for evidence spotting rather than strict temporal span overlap; (3) Adaptive Timestamp Rendering, which adaptively renders timestamps onto video frames using background-aware position and color selection to enhance temporal observability. The three designs are model-agnostic and reciprocal. They effectively improve QA, grounding, and grounded QA performance over different backbones. Notably, LOVER built on Time-R1 achieves new state-of-the-art (SOTA) results among open-source models on popular GQA benchmarks: NExT-GQA and ReXTime. Comprehensive ablation studies further validate the effectiveness of our three innovative components.
%U https://aclanthology.org/2026.emnlp-main.253/
%P 5752-5766

Markdown (Informal)

[Long-to-Short Video Evidence Reasoning for Grounded Question Answering](https://aclanthology.org/2026.emnlp-main.253/) (Chen et al., EMNLP 2026)

• Long-to-Short Video Evidence Reasoning for Grounded Question Answering (Chen et al., EMNLP 2026)

ACL

• Kaiyan Chen, Junbin Xiao, and Xun Yang. 2026. Long-to-Short Video Evidence Reasoning for Grounded Question Answering. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 5752–5766, Budapest, Hungary. Association for Computational Linguistics.