@inproceedings{wasi-etal-2026-large,
title = "Large Language and Vision-Language Models as World Models: A Survey",
author = "Wasi, Azmine Toushik and
Tasnim Meem, Sadia and
Islam, Riashat and
Parvez, Md Rizwan",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.80/",
pages = "1582--1614",
ISBN = "979-8-89176-444-6",
abstract = "Recent advances have reframed Artificial Intelligence (AI) around world models, internal simulators that predict environmental dynamics and support general intelligence. This review surveys Large Language Models (LLMs) and Vision{--}Language Models (VLMs) not merely as text or vision processors, but as predictive systems capable of modeling state, causality, and dynamics. We organize the literature with a dual taxonomy: a theoretical taxonomy covering pixel-space generative simulators, latent-space predictive architectures, neuro-symbolic and code-coupled models, autoregressive foundation models, and hybrid mixtures of world models; and an application taxonomy covering autonomous driving, embodied robotics, interactive simulation and gaming, and social and agentic simulation. Synthesizing recent works, we conclude that although autoregressive transformers exhibit emergent topological and causal reasoning, robust physical world modeling requires moving beyond next-token prediction toward hybrid architectures that integrate generative diffusion models with symbolic grounding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wasi-etal-2026-large">
<titleInfo>
<title>Large Language and Vision-Language Models as World Models: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadia</namePart>
<namePart type="family">Tasnim Meem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riashat</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rizwan</namePart>
<namePart type="family">Parvez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Recent advances have reframed Artificial Intelligence (AI) around world models, internal simulators that predict environmental dynamics and support general intelligence. This review surveys Large Language Models (LLMs) and Vision–Language Models (VLMs) not merely as text or vision processors, but as predictive systems capable of modeling state, causality, and dynamics. We organize the literature with a dual taxonomy: a theoretical taxonomy covering pixel-space generative simulators, latent-space predictive architectures, neuro-symbolic and code-coupled models, autoregressive foundation models, and hybrid mixtures of world models; and an application taxonomy covering autonomous driving, embodied robotics, interactive simulation and gaming, and social and agentic simulation. Synthesizing recent works, we conclude that although autoregressive transformers exhibit emergent topological and causal reasoning, robust physical world modeling requires moving beyond next-token prediction toward hybrid architectures that integrate generative diffusion models with symbolic grounding.</abstract>
<identifier type="citekey">wasi-etal-2026-large</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.80/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1582</start>
<end>1614</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Language and Vision-Language Models as World Models: A Survey
%A Wasi, Azmine Toushik
%A Tasnim Meem, Sadia
%A Islam, Riashat
%A Parvez, Md Rizwan
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wasi-etal-2026-large
%X Recent advances have reframed Artificial Intelligence (AI) around world models, internal simulators that predict environmental dynamics and support general intelligence. This review surveys Large Language Models (LLMs) and Vision–Language Models (VLMs) not merely as text or vision processors, but as predictive systems capable of modeling state, causality, and dynamics. We organize the literature with a dual taxonomy: a theoretical taxonomy covering pixel-space generative simulators, latent-space predictive architectures, neuro-symbolic and code-coupled models, autoregressive foundation models, and hybrid mixtures of world models; and an application taxonomy covering autonomous driving, embodied robotics, interactive simulation and gaming, and social and agentic simulation. Synthesizing recent works, we conclude that although autoregressive transformers exhibit emergent topological and causal reasoning, robust physical world modeling requires moving beyond next-token prediction toward hybrid architectures that integrate generative diffusion models with symbolic grounding.
%U https://aclanthology.org/2026.findings-aacl.80/
%P 1582-1614
Markdown (Informal)
[Large Language and Vision-Language Models as World Models: A Survey](https://aclanthology.org/2026.findings-aacl.80/) (Wasi et al., Findings 2026)
ACL