Lightweight Structured Multimodal Reasoning for Clinical Scene Understanding in Robotics

• URL: http://arxiv.org/abs/2509.22014v1
• Date: Fri, 26 Sep 2025 07:49:49 GMT
• Title: Lightweight Structured Multimodal Reasoning for Clinical Scene Understanding in Robotics
• Abstract summary: We present a lightweight agentic multimodal framework for video-based scene understanding.<n>It supports chain-of-thought reasoning, speech-vision fusion, and dynamic tool invocation.
• Score: 4.253383204461325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Healthcare robotics requires robust multimodal perception and reasoning to ensure safety in dynamic clinical environments. Current Vision-Language Models (VLMs) demonstrate strong general-purpose capabilities but remain limited in temporal reasoning, uncertainty estimation, and structured outputs needed for robotic planning. We present a lightweight agentic multimodal framework for video-based scene understanding. Combining the Qwen2.5-VL-3B-Instruct model with a SmolAgent-based orchestration layer, it supports chain-of-thought reasoning, speech-vision fusion, and dynamic tool invocation. The framework generates structured scene graphs and leverages a hybrid retrieval module for interpretable and adaptive reasoning. Evaluations on the Video-MME benchmark and a custom clinical dataset show competitive accuracy and improved robustness compared to state-of-the-art VLMs, demonstrating its potential for applications in robot-assisted surgery, patient monitoring, and decision support.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• Volumetric Radiology AI in the Era of Multimodal Large Language Models [62.95443321443533]
  Volumetric radiology presents a fundamental representational mismatch.<n>Current large language models (MLLMs) are conditioned on selected two-dimensional (2D) images, compressed visual representations, or report-derived text.<n>Reliable radiology AI requires representations that preserve task-relevant 3D information and systems that can access, verify, and integrate this information.
  arXiv  Detail & Related papers  (2026-08-20T20:23:41Z)
• A Unified Benchmark for RCM-Constrained Visual Servoing: Modeling-Controller Interaction and Robustness Analysis in Laparoscopic Robots [8.534283053772247]
  In robot-assisted laparoscopic minimally invasive surgery (MIS), accurate enforcement of the remote center of motion (RCM) constraint is critical for safe and stable automatic field-of-view (FoV) adjustment.<n>This paper presents an open-source simulation framework integrating three representative RCM modeling approaches and six IBVS-based control architectures.
  arXiv  Detail & Related papers  (2026-06-22T04:56:38Z)
• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models [83.50100003741628]
  Vision and language models (VLMs) hold immense promise to transform biomedical imaging.<n>We introduce the Massive Multimodal Biomedical Understanding (MMBU) benchmark.<n>It is the largest vision and language benchmark to date, covering 35 submodalities with rich structured metadata.
  arXiv  Detail & Related papers  (2026-06-04T20:24:47Z)
• Research on Vision-Language Question Answering Models for Industrial Robots [6.470944338393257]
  A hierarchical cross-modal fusion model is proposed for vision-language question answering (VLQA) in industrial robotics.<n>The framework integrates advanced object detection, multi-scale visual encoding, syntactic parsing, and task-aware semantic attention to unite vision and language signals into a joint reasoning space.
  arXiv  Detail & Related papers  (2026-05-02T15:11:48Z)
• Agentic AI for Personalized Physiotherapy: A Multi-Agent Framework for Generative Video Training and Real-Time Pose Correction [0.0]
  We propose a novel Multi-Agent System (MAS) architecture that leverages Generative AI and computer vision to close the tele-rehabilitation loop.<n>We present the system architecture, detail the prototype pipeline using Large Language Models and MediaPipe, and outline our clinical evaluation plan.
  arXiv  Detail & Related papers  (2026-04-22T23:47:51Z)
• Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling [24.896312231457653]
  We develop a framework to profile and handle missing modalities while addressing the canonical desideratum of safe, transparent clinical AI.<n>We show that autoregressive sequence modeling with transformer-based architectures outperforms baselines on the MIMIC-IV and eICU fine-tuning benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T18:55:56Z)
• From Perception to Action: An Interactive Benchmark for Vision Reasoning [51.11355591375073]
  Causal Hierarchy of Actions and Interactions (CHAIN) benchmark designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints.<n> CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing.<n>Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions.
  arXiv  Detail & Related papers  (2026-02-24T15:33:02Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis [10.584087870930354]
  We propose a new multimodal agent framework, Vision-Interleaved Chain-of-Thought Framework (VICoT)<n>VICoT implements explicit multi-round reasoning by dynamically incorporating visual tools into the chain of thought.<n>We also propose the Reasoning Stack distillation method to migrate complex Agent behaviors to small, lightweight models.
  arXiv  Detail & Related papers  (2025-11-25T09:00:28Z)
• Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis [13.589690091116802]
  Cross-modal medical image synthesis research focuses on reconstructing missing imaging modalities from available ones to support clinical diagnosis.<n>How can we model the heterogeneous contributions of different modalities to various target tasks?<n>How can we maintain modality identity consistency in multi-output generation?
  arXiv  Detail & Related papers  (2025-10-03T08:47:17Z)
• FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning [65.42201665046505]
  Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question.<n>This static approach limits their ability to adaptively gather visual evidence, leading to suboptimal performance on tasks that require broad temporal coverage or fine-grained spatial detail.<n>We introduce FrameMind, an end-to-end framework trained with reinforcement learning that enables models to dynamically request visual information during reasoning through Frame-Interleaved Chain-of-Thought (FiCOT)<n>Unlike traditional approaches, FrameMind operates in multiple turns where the model alternates between textual reasoning and active visual perception, using tools to extract
  arXiv  Detail & Related papers  (2025-09-28T17:59:43Z)
• Baichuan-M2: Scaling Medical Capability with Large Verifier System [40.86227022086866]
  We introduce a novel dynamic verification framework that moves beyond static answer verifier.<n>We develop Baichuan-M2, a medical augmented reasoning model trained through a multi-stage reinforcement learning strategy.<n> evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts.
  arXiv  Detail & Related papers  (2025-09-02T11:23:35Z)
• Foundation Model for Skeleton-Based Human Action Understanding [56.89025287217221]
  This paper presents a Unified Skeleton-based Dense Representation Learning framework.<n>USDRL consists of a Transformer-based Dense Spatio-Temporal (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT)
  arXiv  Detail & Related papers  (2025-08-18T02:42:16Z)
• MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving [63.875372281596576]
  MetAdv is a novel adversarial testing platform that enables realistic, dynamic, and interactive evaluation.<n>It supports flexible 3D vehicle modeling and seamless transitions between simulated and physical environments.<n>It enables real-time capture of physiological signals and behavioral feedback from drivers.
  arXiv  Detail & Related papers  (2025-08-04T03:07:54Z)
• AURA: A Multi-Modal Medical Agent for Understanding, Reasoning & Annotation [0.8397730500554048]
  AURA is the first visual linguistic explainability agent designed specifically for comprehensive analysis, explanation, and evaluation of medical images.<n>AURA represents a significant advancement toward more transparent, adaptable, and clinically aligned AI systems.
  arXiv  Detail & Related papers  (2025-07-22T18:24:18Z)
• MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report [4.340464264725625]
  We introduce a novel Multi-Modal Contrastive Pre-training Framework that synergistically combines X-rays, electrocardiograms (ECGs) and radiology/cardiology reports. We utilize LoRA-Peft to significantly reduce trainable parameters in the LLM and incorporate recent linear attention dropping strategy in the Vision Transformer(ViT) for smoother attention. To the best of our knowledge, we are the first to propose an integrated model that combines X-ray, ECG, and Radiology/Cardiology Report with this approach.
  arXiv  Detail & Related papers  (2024-10-21T17:42:41Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• Extending Process Discovery with Model Complexity Optimization and Cyclic States Identification: Application to Healthcare Processes [62.997667081978825]
  The paper presents an approach to process mining providing semi-automatic support to model optimization. A model simplification approach is proposed, which essentially abstracts the raw model at the desired granularity. We aim to demonstrate the capabilities of the technological solution using three datasets from different applications in the healthcare domain.
  arXiv  Detail & Related papers  (2022-06-10T16:20:59Z)

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.