Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

• URL: http://arxiv.org/abs/2506.21876v1
• Date: Fri, 27 Jun 2025 03:24:29 GMT
• Title: Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
• Authors: 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,
• Abstract summary: Internal world models (WMs) enable agents to understand the world's state and predict transitions.<n>Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs.
• Score: 54.3628937181904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Internal world models (WMs) enable agents to understand the world's state and predict transitions, serving as the basis for advanced deliberative reasoning. Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs. While the latest studies have evaluated and shown limitations in specific capabilities such as visual understanding, a systematic evaluation of VLMs' fundamental WM abilities remains absent. Drawing on comparative psychology and cognitive science, we propose a two-stage framework that assesses Perception (visual, spatial, temporal, quantitative, and motion) and Prediction (mechanistic simulation, transitive inference, compositional inference) to provide an atomic evaluation of VLMs as WMs. Guided by this framework, we introduce WM-ABench, a large-scale benchmark comprising 23 fine-grained evaluation dimensions across 6 diverse simulated environments with controlled counterfactual simulations. Through 660 experiments on 15 latest commercial and open-source VLMs, we find that these models exhibit striking limitations in basic world modeling abilities. For instance, almost all models perform at near-random accuracy when distinguishing motion trajectories. Additionally, they lack disentangled understanding -- e.g., some models tend to believe blue objects move faster than green ones. More rich results and analyses reveal significant gaps between VLMs and human-level world modeling.

Related papers

• Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language Models [5.134872455507186]
  This paper presents a systematic evaluation of state-of-the-art multimodal large language models (MLLMs) on intuitive physics tasks.<n>We assess the open-source models InternVL 2.5, Qwen 2.5 VL, LLaVA-OneVision, and the proprietary Gemini 2.0 Flash Thinking.<n>We find that even the latest models struggle to reliably distinguish physically plausible from implausible scenarios.
  arXiv  Detail & Related papers  (2025-07-22T13:24:42Z)
• From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models [17.235722538085263]
  This study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of Theory of Mind (ToM) in large language models (MLLMs)<n>We first construct a multimodal ToM test dataset, GridToM, which incorporates diverse belief testing tasks and perceptual information from multiple perspectives.<n>Next, our analysis shows that attention heads in multimodal large models can distinguish cognitive information across perspectives, providing evidence of ToM capabilities.
  arXiv  Detail & Related papers  (2025-06-17T06:27:42Z)
• SlotPi: Physics-informed Object-centric Reasoning Models [37.32107835829927]
  We introduce SlotPi, a physics-informed object-centric reasoning model.<n>Our experiments highlight the model's strengths in tasks such as prediction and Visual Question Answering (VQA) on benchmark and fluid datasets.<n>We have created a real-world dataset encompassing object interactions, fluid dynamics, and fluid-object interactions, on which we validated our model's capabilities.
  arXiv  Detail & Related papers  (2025-06-12T14:53:36Z)
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning [52.36434784963598]
  We introduce WorldPrediction, a video-based benchmark for evaluating world modeling and procedural planning capabilities of different AI models.<n>We show that current frontier models barely achieve 57% accuracy on WorldPrediction-WM and 38% on WorldPrediction-PP whereas humans are able to solve both tasks perfectly.
  arXiv  Detail & Related papers  (2025-06-04T18:22:40Z)
• WorldSimBench: Towards Video Generation Models as World Simulators [79.69709361730865]
  We classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.
  arXiv  Detail & Related papers  (2024-10-23T17:56:11Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective [2.61072980439312]
  Devising formalisms to develop internal world models is a critical research challenge in the domains of artificial intelligence and machine learning. This thesis identifies several limitations with the prevalent use of state space models as internal world models. The structure of models in formalisms facilitates exact probabilistic inference using belief propagation, as well as end-to-end learning via backpropagation through time. These formalisms integrate the concept of uncertainty in world states, thus improving the system's capacity to emulate the nature of the real world and quantify the confidence in its predictions.
  arXiv  Detail & Related papers  (2024-04-24T12:41:04Z)
• Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models [73.40350756742231]
  Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored.
  arXiv  Detail & Related papers  (2024-02-12T18:21:14Z)
• EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning [84.6451394629312]
  We introduce EgoPlan-Bench, a benchmark to evaluate the planning abilities of MLLMs in real-world scenarios. We show that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. We also present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench.
  arXiv  Detail & Related papers  (2023-12-11T03:35:58Z)
• MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models [103.9987158554515]
  MultiViz is a method for analyzing the behavior of multimodal models by scaffolding the problem of interpretability into 4 stages. We show that the complementary stages in MultiViz together enable users to simulate model predictions, assign interpretable concepts to features, perform error analysis on model misclassifications, and use insights from error analysis to debug models.
  arXiv  Detail & Related papers  (2022-06-30T18:42:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.