@inproceedings{park-etal-2026-latent,
title = "Latent-Level Uncertainty Resolution for Stable {EEG}-to-Text Decoding under Cross-Subject Variability",
author = "Park, Sejin and
Lee, Jedong and
So, Yunhui and
Kim, Byung Hyung",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1350/",
pages = "28666--28679",
ISBN = "979-8-89176-462-0",
abstract = "Autoregressive generators often rely on fixed conditioning representations, so uncertainty in noisy inputs can be amplified during rollout under distribution shift. We address this by resolving uncertainty in latent space before decoding: Latent-Level Uncertainty Resolution (LURS) encodes inputs as stochastic latent sequences and learns a denoising refinement operator. At inference, a single deterministic refinement step, without reference tokens or iterative sampling, feeds a refined latent memory to the decoder via cross-attention. In teacher-forced and teacher-forcing-free decoding on open-vocabulary EEG-to-text, LURS improves generation quality and substantially reduces cross-subject variability, while remaining competitive in shared-subject settings. Ablations and stability analysis attribute gains to latent refinement rather than decoder changes or hyperparameter effects."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-latent">
<titleInfo>
<title>Latent-Level Uncertainty Resolution for Stable EEG-to-Text Decoding under Cross-Subject Variability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sejin</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jedong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunhui</namePart>
<namePart type="family">So</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byung</namePart>
<namePart type="given">Hyung</namePart>
<namePart type="family">Kim</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Autoregressive generators often rely on fixed conditioning representations, so uncertainty in noisy inputs can be amplified during rollout under distribution shift. We address this by resolving uncertainty in latent space before decoding: Latent-Level Uncertainty Resolution (LURS) encodes inputs as stochastic latent sequences and learns a denoising refinement operator. At inference, a single deterministic refinement step, without reference tokens or iterative sampling, feeds a refined latent memory to the decoder via cross-attention. In teacher-forced and teacher-forcing-free decoding on open-vocabulary EEG-to-text, LURS improves generation quality and substantially reduces cross-subject variability, while remaining competitive in shared-subject settings. Ablations and stability analysis attribute gains to latent refinement rather than decoder changes or hyperparameter effects.</abstract>
<identifier type="citekey">park-etal-2026-latent</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1350/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>28666</start>
<end>28679</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latent-Level Uncertainty Resolution for Stable EEG-to-Text Decoding under Cross-Subject Variability
%A Park, Sejin
%A Lee, Jedong
%A So, Yunhui
%A Kim, Byung Hyung
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F park-etal-2026-latent
%X Autoregressive generators often rely on fixed conditioning representations, so uncertainty in noisy inputs can be amplified during rollout under distribution shift. We address this by resolving uncertainty in latent space before decoding: Latent-Level Uncertainty Resolution (LURS) encodes inputs as stochastic latent sequences and learns a denoising refinement operator. At inference, a single deterministic refinement step, without reference tokens or iterative sampling, feeds a refined latent memory to the decoder via cross-attention. In teacher-forced and teacher-forcing-free decoding on open-vocabulary EEG-to-text, LURS improves generation quality and substantially reduces cross-subject variability, while remaining competitive in shared-subject settings. Ablations and stability analysis attribute gains to latent refinement rather than decoder changes or hyperparameter effects.
%U https://aclanthology.org/2026.findings-emnlp.1350/
%P 28666-28679
Markdown (Informal)
[Latent-Level Uncertainty Resolution for Stable EEG-to-Text Decoding under Cross-Subject Variability](https://aclanthology.org/2026.findings-emnlp.1350/) (Park et al., Findings 2026)
ACL