Magma: A Foundation Model for Multimodal AI Agents

• URL: http://arxiv.org/abs/2502.13130v1
• Date: Tue, 18 Feb 2025 18:55:21 GMT
• Title: Magma: A Foundation Model for Multimodal AI Agents
• Authors: Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Lars Liden, Jianfeng Gao,
• Abstract summary: Magma is a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data.
• Score: 85.53847140774839
• License:
• Abstract: We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.

Related papers

• Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models [79.59567114769513]
  We introduce Migician, the first multi-image grounding model capable of performing free-form and accurate grounding across multiple images. Our model achieves significantly superior multi-image grounding capabilities, outperforming the best existing MLLMs by 24.94% and even surpassing much larger 70B models.
  arXiv  Detail & Related papers  (2025-01-10T07:56:23Z)
• GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control [122.65089441381741]
  We present GEM, a Generalizable Ego-vision Multimodal world model. It predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Our dataset is comprised of 4000+ hours of multimodal data across domains like autonomous driving, egocentric human activities, and drone flights.
  arXiv  Detail & Related papers  (2024-12-15T14:21:19Z)
• LLaRA: Supercharging Robot Learning Data for Vision-Language Policy [56.505551117094534]
  We introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control.
  arXiv  Detail & Related papers  (2024-06-28T17:59:12Z)
• LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning [50.99807031490589]
  We introduce LLARVA, a model trained with a novel instruction tuning method to unify a range of robotic learning tasks, scenarios, and environments. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model. Experiments yield strong performance, demonstrating that LLARVA performs well compared to several contemporary baselines.
  arXiv  Detail & Related papers  (2024-06-17T17:55:29Z)
• An Interactive Agent Foundation Model [49.77861810045509]
  We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare.
  arXiv  Detail & Related papers  (2024-02-08T18:58:02Z)
• RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models [4.4173427917548524]
  Multimodal Large Language Models (MLLMs) have emerged as novel backbones for various downstream tasks. We introduce the RoboLLM framework, equipped with a BEiT-3 backbone, to address all visual perception tasks in the ARMBench challenge.
  arXiv  Detail & Related papers  (2023-10-16T09:30:45Z)
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models [38.503337052122234]
  Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation. We aim to synthesize robot trajectories for a variety of manipulation tasks given an open-set of instructions and an open-set of objects. We demonstrate how the proposed framework can benefit from online experiences by efficiently learning a dynamics model for scenes that involve contact-rich interactions.
  arXiv  Detail & Related papers  (2023-07-12T07:40:48Z)

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.