<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bai-etal-2026-egoactor">
    <titleInfo>
        <title>EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Bai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">MingMing</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chaojie</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyi</namePart>
        <namePart type="family">Bai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinlong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Börje</namePart>
        <namePart type="given">F</namePart>
        <namePart type="family">Karlsson</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>Deploying humanoid robots in real-world environments requires tightly integrating perception, locomotion, and manipulation under partial observations, dynamic changes, and frequent transitions across heterogeneous sub-tasks. Towards this challenge, we propose EgoActing, a new task that grounds high-level instructions into diverse, precise, and spatially aware humanoid actions. We instantiate it with EgoActor, a hierarchical humanoid system centered on a vision-language model that predicts egocentric textual actions from monocular RGB observations. Among the actions, parameterized movement and viewpoint actions are mapped to locomotion and head controllers, while manipulation and human-interaction actions are routed to downstream skills via lightweight parsing. Trained with broad supervision from real-world egocentric demonstrations, spatial reasoning QA, and simulated demonstrations, EgoActor makes robust, context-aware decisions with a sub-second VLM forward pass for both 8B and 4B variants, while the current cloud-deployed robot loop takes 3–8 seconds end-to-end. Extensive simulated and real-world evaluations show that EgoActor bridges abstract task planning and concrete motor execution, generalizing across diverse tasks and unseen environments. Code and models are released at https://baai-agents.github.io/RoboNoid/EgoActor/.</abstract>
    <identifier type="citekey">bai-etal-2026-egoactor</identifier>
    <identifier type="doi">10.18653/2026.findings-emnlp.1136</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1136/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>24059</start>
            <end>24083</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models
%A Bai, Yu
%A Yu, MingMing
%A Li, Chaojie
%A Bai, Ziyi
%A Wang, Xinlong
%A Karlsson, Börje F.
%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 bai-etal-2026-egoactor
%X Deploying humanoid robots in real-world environments requires tightly integrating perception, locomotion, and manipulation under partial observations, dynamic changes, and frequent transitions across heterogeneous sub-tasks. Towards this challenge, we propose EgoActing, a new task that grounds high-level instructions into diverse, precise, and spatially aware humanoid actions. We instantiate it with EgoActor, a hierarchical humanoid system centered on a vision-language model that predicts egocentric textual actions from monocular RGB observations. Among the actions, parameterized movement and viewpoint actions are mapped to locomotion and head controllers, while manipulation and human-interaction actions are routed to downstream skills via lightweight parsing. Trained with broad supervision from real-world egocentric demonstrations, spatial reasoning QA, and simulated demonstrations, EgoActor makes robust, context-aware decisions with a sub-second VLM forward pass for both 8B and 4B variants, while the current cloud-deployed robot loop takes 3–8 seconds end-to-end. Extensive simulated and real-world evaluations show that EgoActor bridges abstract task planning and concrete motor execution, generalizing across diverse tasks and unseen environments. Code and models are released at https://baai-agents.github.io/RoboNoid/EgoActor/.
%R 10.18653/2026.findings-emnlp.1136
%U https://aclanthology.org/2026.findings-emnlp.1136/
%U https://doi.org/10.18653/2026.findings-emnlp.1136
%P 24059-24083

Markdown (Informal)

[EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models](https://aclanthology.org/2026.findings-emnlp.1136/) (Bai et al., Findings 2026)

• EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models (Bai et al., Findings 2026)

ACL

• Yu Bai, MingMing Yu, Chaojie Li, Ziyi Bai, Xinlong Wang, and Börje F. Karlsson. 2026. EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 24059–24083, Budapest, Hungary. Association for Computational Linguistics.