Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces

• URL: http://arxiv.org/abs/2506.00123v1
• Date: Fri, 30 May 2025 18:00:34 GMT
• Title: Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
• Authors: Gen Luo, Ganlin Yang, Ziyang Gong, Guanzhou Chen, Haonan Duan, Erfei Cui, Ronglei Tong, Zhi Hou, Tianyi Zhang, Zhe Chen, Shenglong Ye, Lewei Lu, Jingbo Wang, Wenhai Wang, Jifeng Dai, Yu Qiao, Rongrong Ji, Xizhou Zhu,
• Abstract summary: VeBrain is a unified framework for perception, reasoning, and control in real world.<n>VeBrain reformulates robotic control into common text-based MLLM tasks in the 2D visual space.<n>VeBrain shows strong adaptability, flexibility, and compositional capabilities compared to existing methods.
• Score: 90.96731971685115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The remarkable progress of Multimodal Large Language Models (MLLMs) has attracted increasing attention to extend them to physical entities like legged robot. This typically requires MLLMs to not only grasp multimodal understanding abilities, but also integrate visual-spatial reasoning and physical interaction capabilities. Nevertheless,existing methods struggle to unify these capabilities due to their fundamental differences.In this paper, we present the Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world. VeBrain reformulates robotic control into common text-based MLLM tasks in the 2D visual space, thus unifying the objectives and mapping spaces of different tasks. Then, a novel robotic adapter is proposed to convert textual control signals from MLLMs to motion policies of real robots. From the data perspective, we further introduce VeBrain-600k, a high-quality instruction dataset encompassing various capabilities of VeBrain. In VeBrain-600k, we take hundreds of hours to collect, curate and annotate the data, and adopt multimodal chain-of-thought(CoT) to mix the different capabilities into a single conversation. Extensive experiments on 13 multimodal benchmarks and 5 spatial intelligence benchmarks demonstrate the superior performance of VeBrain to existing MLLMs like Qwen2.5-VL. When deployed to legged robots and robotic arms, VeBrain shows strong adaptability, flexibility, and compositional capabilities compared to existing methods. For example, compared to Qwen2.5-VL, VeBrain not only achieves substantial gains on MMVet by +5.6%, but also excels in legged robot tasks with +50% average gains.

Related papers

• Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in the Brain [25.98830728450583]
  multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models.<n>We show that instruction-tuned video MLLMs significantly outperform non-instruction-tuned multimodal and unimodal models.<n>Our evaluation of MLLMs for both video and audio tasks using language-guided instructions shows clear disentanglement in task-specific representations from MLLMs.
  arXiv  Detail & Related papers  (2025-06-09T22:48:36Z)
• Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain) [22.244699182222824]
  Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity.<n>Recently, a new class of instruction-tuned multimodal LLMs have emerged, showing remarkable zero-shot capabilities in open-ended multimodal vision tasks.<n>We investigate whether MLLMs, when prompted with natural instructions, lead to better brain alignment and effectively capture instruction-specific representations.
  arXiv  Detail & Related papers  (2025-05-26T14:18:15Z)
• RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete [27.814422322892522]
  Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various multimodal contexts.<n>They lack three essential robotic brain capabilities: Planning Capability, Affordance Perception, and Trajectory Prediction.<n>We introduce ShareRobot, a dataset that labels multi-dimensional information such as task planning, object affordance, and end-effector trajectory.<n>We develop RoboBrain, an MLLM-based model that combines robotic and general multi-modal data, utilizing a multi-stage training strategy.
  arXiv  Detail & Related papers  (2025-02-28T17:30:39Z)
• MMRo: Are Multimodal LLMs Eligible as the Brain for In-Home Robotics? [33.573056018368504]
  This study introduces the first benchmark for evaluating Multimodal LLM for Robotic (MMRo) benchmark. We identify four essential capabilities perception, task planning, visual reasoning, and safety measurement that MLLMs must possess to qualify as the robot's central processing unit. Our findings indicate that no single model excels in all areas, suggesting that current MLLMs are not yet trustworthy enough to serve as the cognitive core for robots.
  arXiv  Detail & Related papers  (2024-06-28T07:09:06Z)
• Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models [71.93366651585275]
  Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. We propose Visualization-of-Thought (VoT) to elicit spatial reasoning of LLMs by visualizing their reasoning traces. VoT significantly enhances the spatial reasoning abilities of LLMs.
  arXiv  Detail & Related papers  (2024-04-04T17:45:08Z)
• Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models [76.99140362751787]
  We present NuInstruct, a novel dataset with 91K multi-view video-QA pairs across 17 subtasks. We also present BEV-InMLLM, an end-to-end method for efficiently deriving instruction-aware Bird's-Eye-View features.
  arXiv  Detail & Related papers  (2024-01-02T01:54:22Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• LLM as A Robotic Brain: Unifying Egocentric Memory and Control [77.0899374628474]
  Embodied AI focuses on the study and development of intelligent systems that possess a physical or virtual embodiment (i.e. robots) Memory and control are the two essential parts of an embodied system and usually require separate frameworks to model each of them. We propose a novel framework called LLM-Brain: using Large-scale Language Model as a robotic brain to unify egocentric memory and control.
  arXiv  Detail & Related papers  (2023-04-19T00:08:48Z)
• Multimodal foundation models are better simulators of the human brain [65.10501322822881]
  We present a newly-designed multimodal foundation model pre-trained on 15 million image-text pairs. We find that both visual and lingual encoders trained multimodally are more brain-like compared with unimodal ones.
  arXiv  Detail & Related papers  (2022-08-17T12:36:26Z)

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.