@inproceedings{yu-etal-2026-waymoqa,
title = "{W}aymo{QA}: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving",
author = "Yu, Seungjun and
Lee, Seonho and
Kim, Namho and
Shin, Jaeyo and
Park, Junsung and
Ryu, Wonjeong and
Jung, Raehyuk and
Shim, Hyunjung",
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.1028/",
doi = "10.18653/2026.findings-emnlp.1028",
pages = "21721--21744",
ISBN = "979-8-89176-462-0",
abstract = "In real-world driving, resolving a primary hazard often precipitates a secondary one: swerving to avoid a stalled vehicle may force the ego car into oncoming traffic. Existing driving QA datasets fail to capture this cascading causality, evaluating perception, prediction, and planning in silos without anticipating the risks action induces. We introduce WaymoQA, a multi-view dataset that frames safety-critical reasoning as a two-stage task: resolving the immediate threat, then mitigating the action-induced secondary risk. WaymoQA provides 35,000 human-annotated QA pairs across image and video modalities, with 28K training and 6.4K test examples. Experiments show that SOTA models struggle on safety-critical scenes, while fine-tuning on WaymoQA improves both reasoning accuracy and consistency. WaymoQA thus serves as a rigorous benchmark and resource for safety-aware autonomous driving."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-waymoqa">
<titleInfo>
<title>WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seungjun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Namho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeyo</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junsung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonjeong</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raehyuk</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunjung</namePart>
<namePart type="family">Shim</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>In real-world driving, resolving a primary hazard often precipitates a secondary one: swerving to avoid a stalled vehicle may force the ego car into oncoming traffic. Existing driving QA datasets fail to capture this cascading causality, evaluating perception, prediction, and planning in silos without anticipating the risks action induces. We introduce WaymoQA, a multi-view dataset that frames safety-critical reasoning as a two-stage task: resolving the immediate threat, then mitigating the action-induced secondary risk. WaymoQA provides 35,000 human-annotated QA pairs across image and video modalities, with 28K training and 6.4K test examples. Experiments show that SOTA models struggle on safety-critical scenes, while fine-tuning on WaymoQA improves both reasoning accuracy and consistency. WaymoQA thus serves as a rigorous benchmark and resource for safety-aware autonomous driving.</abstract>
<identifier type="citekey">yu-etal-2026-waymoqa</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1028</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1028/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>21721</start>
<end>21744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving
%A Yu, Seungjun
%A Lee, Seonho
%A Kim, Namho
%A Shin, Jaeyo
%A Park, Junsung
%A Ryu, Wonjeong
%A Jung, Raehyuk
%A Shim, Hyunjung
%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 yu-etal-2026-waymoqa
%X In real-world driving, resolving a primary hazard often precipitates a secondary one: swerving to avoid a stalled vehicle may force the ego car into oncoming traffic. Existing driving QA datasets fail to capture this cascading causality, evaluating perception, prediction, and planning in silos without anticipating the risks action induces. We introduce WaymoQA, a multi-view dataset that frames safety-critical reasoning as a two-stage task: resolving the immediate threat, then mitigating the action-induced secondary risk. WaymoQA provides 35,000 human-annotated QA pairs across image and video modalities, with 28K training and 6.4K test examples. Experiments show that SOTA models struggle on safety-critical scenes, while fine-tuning on WaymoQA improves both reasoning accuracy and consistency. WaymoQA thus serves as a rigorous benchmark and resource for safety-aware autonomous driving.
%R 10.18653/2026.findings-emnlp.1028
%U https://aclanthology.org/2026.findings-emnlp.1028/
%U https://doi.org/10.18653/2026.findings-emnlp.1028
%P 21721-21744
Markdown (Informal)
[WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving](https://aclanthology.org/2026.findings-emnlp.1028/) (Yu et al., Findings 2026)
ACL
- Seungjun Yu, Seonho Lee, Namho Kim, Jaeyo Shin, Junsung Park, Wonjeong Ryu, Raehyuk Jung, and Hyunjung Shim. 2026. WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 21721–21744, Budapest, Hungary. Association for Computational Linguistics.