Sign in to view source links and access this dataset
Description
Magma is a foundation model for multimodal AI agents, developed by researchers from Microsoft Research, University of Maryland, University of Wisconsin-Madison, KAIST, and University of Washington. The associated dataset, Magma-AITW-SoM, likely serves as a benchmark for evaluating multimodal agent capabilities. The dataset page was last updated on 2025-04-29.
Use Cases
Benchmarking multimodal reasoning and planning capabilities of AI agents based on the described model.
Training or fine-tuning multimodal AI agents on tasks implied by the 'AITW-SoM' benchmark name.
Conducting ablation studies on agent architectures using the provided multimodal data.
Strengths
Associated with a published foundation model research project from multiple academic and industry institutions.
Dataset page was updated on 2025-04-29, indicating recent maintenance.
Limitations
Dataset size, row count, and specific column structure are unknown, limiting suitability assessment.
Column-level documentation is absent; field semantics must be inferred after download.
License information is unavailable, which may restrict usage.
Provenance
Source
MagmaAI, a collaboration involving Microsoft Research and several universities.
Collection Method
Likely created as a benchmark for the Magma foundation model research.
Freshness
Last updated 2025-04-29 08:08:43.
License is unknown; users must verify terms of use before application.