Pith. sign in

REVIEW 1 cited by

MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks

Not yet reviewed by Pith; the record is open.

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 2303.16839 v3 pith:3CTVALZJ submitted 2023-03-29 cs.CV cs.CLcs.LG

classification cs.CVcs.CLcs.LG
keywords tasksmodellearningarchitecturemultimodalsimpleaccommodateapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is able to accommodate contrastive and generative learning by a novel two-pass approach on the text decoder. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Furthermore, the same architecture enables straightforward extensions to open-vocabulary object detection and video-language tasks. The model tackles a diverse range of tasks, while being modest in capacity. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models. It shows very competitive results on VQA and Video Captioning, especially considering its capacity. Ablations confirm the flexibility and advantages of our approach.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Temporal Object Captioning for Street Scene Videos from LiDAR Tracks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A rule-based pipeline converts LiDAR tracks into template captions of traffic dynamics, and training SwinBERT on them lowers the Visual Bias Measure across three datasets.

Pith tools