Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
Similar Papers
Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics (2026.findings-acl)
Copied to clipboard
| Challenge: | unified vision–language models (VLMs) struggle to generate physically plausible transitions between frames from instructions. |
| Approach: | They find that VLMs struggle to generate physically plausible transitions between frames from instructions. |
| Outcome: | The proposed model outperforms state-of-the-art image editing models on Aurora-Bench . it achieves the best average human evaluation across all subsets of Aurora-bench compared with other models . |
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities (2025.acl-long)
Copied to clipboard
| Challenge: | Vision-language Models have been shown to be highly capable but lacking basic visual understanding skills. |
| Approach: | They propose to examine the limitations of vision-language models on visual tasks by constructing a series of tests that probe which components of design may be lacking. |
| Outcome: | The proposed tests compare VLMs to other models on visual encoders, intermediate vision-language projection and LLM-decoder outputs. |
Can Language Models Serve as Text-Based World Simulators? (2024.acl-short)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have pointed towards an alternative approach by leveraging the huge amount of knowledge contained in their pre-training datasets. |
| Approach: | They build and use a benchmark to quantify how well text-based simulators can serve as text-driven world simulators. |
| Outcome: | The proposed benchmark aims to quantify how well language models can serve as world simulators. |
MVP-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LVLMs perform visual perception at multiple levels, but they are not able to perform multi-level tasks. |
| Approach: | They propose a visual–language benchmark to evaluate LVLMs' perceptions . they use manipulated images to examine how LVLs can perform multi-level tasks . |
| Outcome: | The proposed model performs poorly on high-level perception tasks, the authors show . they also show that current models do not generalize in understanding semantics of synthetic images . |
Can Language Models Understand Physical Concepts? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing language models do not understand basic physical concepts in the human world. |
| Approach: | They propose a method to transfer embodied knowledge from visual models to LMs . they use visual concepts and embodies concepts learned from interaction with the world . |
| Outcome: | The proposed method achieves comparable performance with scaling up parameters of LMs 134. |
From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)
Copied to clipboard
Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, Heng Ji
| Challenge: | Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time. |
| Approach: | They propose a framework that reframes language modeling as next-state prediction under interaction. |
| Outcome: | The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics . |
On the Fine-Grained Planning Abilities of VLM Web Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) have shown promise as web agents, yet their planning has been overlooked. |
| Approach: | They propose to examine VLMs’ ability to understand temporal relationships within web contexts and assess plans of actions across diverse scenarios. |
| Outcome: | The proposed models exhibit limited performance in the above skills and are not reliable to function as web agents. |
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens (2025.emnlp-demos)
Copied to clipboard
Hala Sheta, Eric Haoran Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi
| Challenge: | Existing vision-language models are based on exactmatch based accuracy and its derivations to evaluate performance. |
| Approach: | They propose a toolkit that supports systematic benchmarking, analysis, and interpretation of vision-language models by extracting intermediate outputs from any layer during the forward pass of open-source VLMs. |
| Outcome: | The proposed toolkit supports 16 state-of-the-art base VLMs and their over 30 variants and is extensible to accommodate new models without changing the core logic. |
Making Large Language Models into World Models with Precondition and Effect Knowledge (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are not inherently designed to model real-world dynamics, but can be induced to perform two critical world model functions: determining the applicability of an action based on a given world state and predicting the resulting world state upon action execution. |
| Approach: | They propose to use Large Language Models to model world states and preconditions . they validate that precondition and effect knowledge generated by LLMs aligns with human understanding of world dynamics . |
| Outcome: | The proposed model can predict valid actions and state transitions, thereby replicating existing models. |
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (2025.findings-naacl)
Copied to clipboard
Guoli Yin, Haoping Bai, Shuang Ma, Feng Nan, Yanchao Sun, Zhaoyang Xu, Shen Ma, Jiarui Lu, Xiang Kong, Aonan Zhang, Dian Ang Yap, Yizhe Zhang, Karsten Ahnert, Vik Kamath, Mathias Berglund, Dominic Walsh, Tobias Gindele, Juergen Wiest, Zhengfeng Lai, Xiaoming Simon Wang, Jiulong Shan, Meng Cao, Ruoming Pang, Zirui Wang
| Challenge: | Existing benchmarks focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. |
| Approach: | They propose a Massive Multitask Agent Understanding benchmark that evaluates LLMs across five domains and offline tasks. |
| Outcome: | The Massive Multitask Agent Understanding (MMAU) benchmark evaluates models across five domains including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics. |