Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language Models

• URL: http://arxiv.org/abs/2507.16572v1
• Date: Tue, 22 Jul 2025 13:24:42 GMT
• Title: Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language Models
• Abstract summary: 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.
• Score: 5.134872455507186
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a systematic evaluation of state-of-the-art multimodal large language models (MLLMs) on intuitive physics tasks using the GRASP and IntPhys 2 datasets. We assess the open-source models InternVL 2.5, Qwen 2.5 VL, LLaVA-OneVision, and the proprietary Gemini 2.0 Flash Thinking, finding that even the latest models struggle to reliably distinguish physically plausible from implausible scenarios. To go beyond performance metrics, we conduct a probing analysis of model embeddings, extracting intermediate representations at key processing stages to examine how well task-relevant information is preserved. Our results show that, depending on task difficulty, a critical vision-language misalignment can emerge: vision encoders successfully capture physical plausibility cues, but this information is not effectively utilized by the language model, leading to failures in reasoning. This misalignment suggests that the primary limitation of MLLMs in intuitive physics tasks is not the vision component but the ineffective integration of visual and linguistic information. Our findings highlight vision-language alignment as a key area for improvement, offering insights for future MLLMs development.

Related papers

• Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models [14.5102059776721]
  Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models.<n>However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge.<n>We explore these failures using two diagnostic paradigms: (1) probing whether visual information is available, via image reconstruction, and (2) measuring multimodal context sensitivity.
  arXiv  Detail & Related papers  (2026-07-28T22:52:34Z)
• Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: From Evaluation to Diagnosis [63.49939245944781]
  We introduce FG-BMK, a comprehensive fine-grained evaluation benchmark containing 1.01 million questions and 0.28 million images.<n>We find that current LVLMs remain inadequate fine-grained recognizers, with failures arising from intertwined bottlenecks in visual representations, semantic grounding, modality alignment, and category-level knowledge.
  arXiv  Detail & Related papers  (2026-06-17T13:23:26Z)
• Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models [84.94288033791346]
  We conduct a detailed diagnostic analysis to unveil a pervasive issue: visual representation degradation in MLLMs.<n>We attribute this phenomenon to a visual sacrifice driven by the singular text-generation objective, where the model compromises its visual fidelity to optimize for answer generation.<n>We propose Predictive Regularization to force degraded intermediate features to predict initial visual features, thereby maintaining the inherent visual attributes of the MLLM's internal representations.
  arXiv  Detail & Related papers  (2026-03-21T13:10:37Z)
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw [57.237152905238084]
  LTD-Bench is a breakthrough benchmark for large language models (LLMs)<n>It transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code.<n> LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.
  arXiv  Detail & Related papers  (2025-11-04T08:11:23Z)
• Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling [3.5408685781175016]
  Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information.<n>We propose a lightweight decoder-based architecture with token-wise dynamic gating for adaptive fusion of linguistic and visual cues.
  arXiv  Detail & Related papers  (2025-10-09T17:10:36Z)
• Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities [54.94982467313341]
  Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems.<n>We set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking.
  arXiv  Detail & Related papers  (2025-07-10T15:26:41Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models [9.474337395173388]
  Physical reasoning remains a significant challenge for Vision-Language Models (VLMs)<n>Fine-tuning is expensive for large models and impractical to repeatedly perform for every task.<n>We introduce Physics Context Builders (PCBs), a novel modular framework where specialized VLMs are fine-tuned to generate detailed physical scene descriptions.
  arXiv  Detail & Related papers  (2024-12-11T18:40:16Z)
• Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities [30.176918208200604]
  Vision-Language Models (VLMs) have emerged as general purpose tools for addressing a variety of complex computer vision problems. These models have been shown to be highly capable, but also lacking some basic visual understanding skills. This paper sets out to understand the limitations of SoTA VLMs on fundamental visual tasks.
  arXiv  Detail & Related papers  (2024-08-13T08:26:32Z)
• 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)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)
• Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models [50.653838482083614]
  This paper introduces a scalable test-bed to assess the capabilities of IT-LVLMs on fundamental computer vision tasks.<n> MERLIM contains over 300K image-question pairs and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs.
  arXiv  Detail & Related papers  (2023-12-03T16:39:36Z)
• GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models [4.354672867211922]
  This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs) We use it to evaluate several state-of-the-art multimodal LLMs. Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models.
  arXiv  Detail & Related papers  (2023-11-15T15:38:28Z)
• UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes [91.24112204588353]
  We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks. We demonstrate the effectiveness of UViM on three diverse and challenging vision tasks.
  arXiv  Detail & Related papers  (2022-05-20T17:47:59Z)

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.