Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models

• URL: http://arxiv.org/abs/2604.03302v1
• Date: Mon, 30 Mar 2026 05:11:45 GMT
• Title: Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
• Abstract summary: This work investigates the first step of physical reasoning, i.e., intuitive physics understanding, revealing substantial limitations in understanding the dynamics of continuum objects.<n>We propose Scene Dynamic Field (SDF), a concise approach that leverages physics simulators within a multi-task fine-tuning framework.<n>SDF substantially improves performance, achieving up to 20.7% gains on fluid tasks while showing strong generalization to unseen physical domains.
• Score: 19.04320007192703
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become an increasingly important research focus. Despite their improvements, current MLLMs struggle significantly with high-level physics reasoning. In this work, we investigate the first step of physical reasoning, i.e., intuitive physics understanding, revealing substantial limitations in understanding the dynamics of continuum objects. To isolate and evaluate this specific capability, we introduce two fundamental benchmark tasks: Next Frame Selection (NFS) and Temporal Coherence Verification (TCV). Our experiments demonstrate that even state-of-the-art MLLMs perform poorly on these foundational tasks. To address this limitation, we propose Scene Dynamic Field (SDF), a concise approach that leverages physics simulators within a multi-task fine-tuning framework. SDF substantially improves performance, achieving up to 20.7% gains on fluid tasks while showing strong generalization to unseen physical domains. This work not only highlights a critical gap in current MLLMs but also presents a promising cost-efficient approach for developing more physically grounded MLLMs. Our code and data are available at https://github.com/andylinx/Scene-Dynamic-Field.

Related papers

• Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World [49.80040477190479]
  Humans inhabit a physical 4D world where geometric structure and semantic content evolve over time.<n>We introduce Dyn-Bench, a large-scale benchmark built from diverse real-world and synthetic video datasets.<n>We find that existing models cannot simultaneously maintain strong performance in both-temporal reasoning and dynamic object grounding.
  arXiv  Detail & Related papers  (2026-03-13T07:42:16Z)
• SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models [60.80050275581661]
  Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities.<n>They lack a grounded understanding of physical dynamics.<n>We present S, a test-time, SIMulation-enabled ACTion Planning framework.<n>Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-05T18:51:03Z)
• PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement [45.990473754456104]
  Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks.<n>We propose PhyVLLM, a physical-guided video-language framework that explicitly incorporates physical motion into Video LLMs.<n>We show that PhyVLLM significantly outperforms state-of-the-art Video LLMs on both physical reasoning and general video understanding tasks.
  arXiv  Detail & Related papers  (2025-12-04T07:28:56Z)
• MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models [45.450035386882824]
  Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-driven reasoning involving motion dynamics and spatial interactions.<n>We present an approach that addresses this gap by translating physical-world context cues into interpretable representations aligned with VLMs' perception, comprehension, and reasoning.
  arXiv  Detail & Related papers  (2025-11-23T09:43:44Z)
• Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models [75.45940282834327]
  We introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs.<n>We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs.<n>Our approach employs a two-stage fine-tuning strategy, resulting in significant improvements across multiple tasks.
  arXiv  Detail & Related papers  (2025-11-03T14:27:00Z)
• Uncovering Emergent Physics Representations Learned In-Context by Large Language Models [1.8749305679160366]
  Large language models (LLMs) exhibit impressive in-context learning (ICL) abilities, enabling them to solve wide range of tasks via textual prompts alone.<n>Here, we investigate the ICL ability of LLMs, especially focusing on their ability to reason about physics.<n>Using a dynamics forecasting task in physical systems as a proxy, we evaluate whether LLMs can learn physics in context.
  arXiv  Detail & Related papers  (2025-08-17T17:49:17Z)
• 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)
• V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models [84.27290155010533]
  We introduce Vision-centric Multiple Abilities Game Evaluation (V-MAGE), a novel game-based evaluation framework.<n>V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios.<n>We show V-MAGE provides actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings.
  arXiv  Detail & Related papers  (2025-04-08T15:43:01Z)
• MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science [62.96434290874878]
  Current Multi-Modal Large Language Models (MLLM) have shown strong capabilities in general visual reasoning tasks.<n>We develop a new framework, named Multi-Modal Scientific Reasoning with Physics Perception and Simulation (MAPS) based on an MLLM.<n>MAPS decomposes expert-level multi-modal reasoning task into physical diagram understanding via a Physical Perception Model (PPM) and reasoning with physical knowledge via a simulator.
  arXiv  Detail & Related papers  (2025-01-18T13:54:00Z)
• Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models [11.282655911647483]
  Physical reasoning remains a significant challenge for Vision-Language Models (VLMs)<n>We introduce Physics Context Builders (PCBs), a modular framework where specialized smaller VLMs are fine-tuned to generate detailed physical scene descriptions.<n>PCBs enable the separation of visual perception from reasoning, allowing us to analyze their relative contributions to physical understanding.
  arXiv  Detail & Related papers  (2024-12-11T18:40:16Z)
• LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models [35.01842161084472]
  We propose a new physical reasoning task and a dataset, dubbed TraySim.<n>Our task involves predicting the dynamics of several objects on a tray that is given an external impact.<n>We present LLMPhy, a zero-shot black-box optimization framework that leverages the physics knowledge and program synthesis abilities of LLMs.<n>Our results show that the combination of the LLM and the physics engine leads to state-of-the-art zero-shot physical reasoning performance.
  arXiv  Detail & Related papers  (2024-11-12T18:56:58Z)
• Physically Grounded Vision-Language Models for Robotic Manipulation [59.143640049407104]
  We propose PhysObjects, an object-centric dataset of 39.6K crowd-sourced and 417K automated physical concept annotations. We show that fine-tuning a vision-language model on PhysObjects improves its understanding of physical object concepts. We incorporate this physically grounded VLM in an interactive framework with a large language model-based robotic planner.
  arXiv  Detail & Related papers  (2023-09-05T20:21:03Z)

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.