Trendoday

UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models

Unified multimodal models can support both visual understanding and generation, yet generative training does not necessarily improve understanding. We argue that this limitation may arise from a misma

  • Upvotes5
–Rank now
#29Peak rank
1Days on list
7Score · 7d
Nov 18, 2026First seen

About this paper

Reformulating generation as progressive prediction of continuous perceptual representations improves visual understanding in unified multimodal models more than discrete-code or latent-flow objectives.

Unified multimodal models can support both visual understanding and generation, yet generative training does not necessarily improve understanding. We argue that this limitation may arise from a mismatch between the representation targeted by generation and the perceptual representation used for understanding. Conventional generation objectives primarily optimize synthesis-oriented spaces such as discrete visual codes or generative latents. We therefore introduce UMM-JEPA, which reformulates generation as progressive prediction of continuous visual-understanding representations. The model constructs a multi-scale representation hierarchy from coarse to fine, while pixel rendering is…

unified multimodal modelsvisual understandingvisual generationgenerative trainingperceptual representationdiscrete visual codesgenerative latentsUMM-JEPAcontinuous visual-understanding representationsmulti-scale representation hierarchy
Upvotes
5
Authors
4
Published
Oct 26, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models was first seen on Hugging Face · Daily papers on Nov 18, 2026. Since then it has appeared in 1 check on 1 different day. Its best position was #29 of 30, reached on Nov 18, 05:28 UTC. It dropped off the list after Nov 18, 05:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 04:5805:1305:2805:4305:58 Nov 18, 05:28 UTC · #29

Last 14 days

Best rank per day (UTC).

Nov 9today

Questions

Is UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 05:28 UTC, after 1 day of trending.

What is the highest rank UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models reached?

#29 on Hugging Face · Daily papers, on Nov 18, 05:28 UTC. Trendoday checks this list every 120 minutes.

How long has UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models been trending?

It was first seen on Nov 18, 2026 and has been on the list on 1 day (1 check) since.