Pith. sign in

REVIEW 3 cited by

AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.16233 v2 pith:BTDYBELR submitted 2024-04-24 cs.LG cs.AI

Zhiqiang Tang , Haoyang Fang , Su Zhou , Taojiannan Yang , Zihan Zhong , Tony Hu , Katrin Kirchhoff , George Karypis This is my paper · ORCID
classification cs.LGcs.AI
keywords autommautomltasksautogluon-multimodalclassificationdesignedfoundationimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

AutoGluon-Multimodal (AutoMM) is introduced as an open-source AutoML library designed specifically for multimodal learning. Distinguished by its exceptional ease of use, AutoMM enables fine-tuning of foundation models with just three lines of code. Supporting various modalities including image, text, and tabular data, both independently and in combination, the library offers a comprehensive suite of functionalities spanning classification, regression, object detection, semantic matching, and image segmentation. Experiments across diverse datasets and tasks showcases AutoMM's superior performance in basic classification and regression tasks compared to existing AutoML tools, while also demonstrating competitive results in advanced tasks, aligning with specialized toolboxes designed for such purposes.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Quickly Tuning Foundation Models for Image Segmentation

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Meta-learning over dataset features and learning curves lets QTT-SEG find SAM fine-tuning configurations that beat zero-shot and a strong AutoML baseline in under three minutes.

  2. Towards Benchmarking Foundation Models for Tabular Data With Text

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A new 13-dataset benchmark shows that adding text embeddings to tabular models usually improves accuracy, but no embedding or downsampling strategy dominates.

  3. BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data

    cs.CV 2025-10 reject novelty 4.0 of 10

    An AutoML/NAS insect classifier that feeds the target order labels into its metadata encoder, making the reported 96.81% accuracy uninformative.

Pith tools