Transferability Between Understanding and Generation in Unified Multimodal Models

• URL: http://arxiv.org/abs/2607.04423v2
• Date: Tue, 07 Jul 2026 07:27:22 GMT
• Title: Transferability Between Understanding and Generation in Unified Multimodal Models
• Abstract summary: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture.<n>We investigate whether training a capability on one task improves the same capability on the other without explicit supervision.
• Score: 35.84666508890256
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied. We investigate $\boldsymbol{\mathsf{transferability}}$ in UMMs: whether training a capability on one task improves the same capability on the other without explicit supervision. Through controlled experiments, we empirically find that transferability depends on architecture-models with fully shared transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none. Leveraging this transferability, we propose a practical training strategy. The most straightforward way to improve a target generative capability (e.g., counting) is to fine-tune generation directly, but this can degrade visual quality due to distribution shift. Instead, we train the corresponding understanding task and let it transfer into generation, which improves capability-specific generative performance while minimizing distribution shift. We validate this across three capabilities-counting, spatial relation, and text recognition/generation-showing that cross-task transferability can be systematically exploited in UMMs.

Related papers

• Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System [90.64481646805855]
  unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model.<n>We investigate their relationship at the representation, task, and system levels in a controlled, structurally native setting.<n>We show that the value of UMMs extends beyond a unified interface: appropriate specialization, shared task knowledge, and end-to-end optimization can turn coexistence into synergy.
  arXiv  Detail & Related papers  (2026-09-01T17:59:59Z)
• OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation [28.67407481470947]
  Multi-task learning is essential in recommender systems to enable complementary learning among diverse user feedback.<n>OneRank is a Transformer-centric multi-task ranking framework that eliminates encoder-predictorprivate separation.<n>OneRank significantly outperforms state-of-the-art baselines in offline and online experiments on large-scale industrial datasets.
  arXiv  Detail & Related papers  (2026-06-15T15:16:17Z)
• Steering Visual Generation in Unified Multimodal Models with Understanding Supervision [42.765106450407814]
  Unified multimodal models are envisioned to bridge the gap between understanding and generation.<n>We propose Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations.
  arXiv  Detail & Related papers  (2026-05-07T07:20:04Z)
• UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception [71.19234323863314]
  We propose a framework to simultaneously recognize driver behavior, driver emotion, vehicle behavior, and traffic context.<n>Our framework incorporates two core components: dual-branch spatial channel multimodal embedding and adaptive feature-decoupled multi-task loss.<n>We evaluate our method on the AIDE dataset, and the experimental results demonstrate that UV-M3TL achieves state-of-the-art performance across all four tasks.
  arXiv  Detail & Related papers  (2026-02-02T03:35:24Z)
• SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards [55.99492656542475]
  We propose textbfSUDER (textbfSelf-improving textbfUnified LMMs with textbfDual stextbfElf-textbfRewards), a framework reinforcing the understanding and generation capabilities of LMMs.
  arXiv  Detail & Related papers  (2025-06-09T17:38:45Z)
• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning [59.001091197106085]
  Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously.<n>Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in tegrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning.<n>We propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner.
  arXiv  Detail & Related papers  (2025-01-12T17:41:23Z)
• Exploring the Transferability of Visual Prompting for Multimodal Large Language Models [47.162575147632396]
  Transferable Visual Prompting (TVP) is a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts.
  arXiv  Detail & Related papers  (2024-04-17T09:39:07Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding [11.608682595506354]
  Multi-task scene understanding aims to design models that can simultaneously predict several scene understanding tasks with one versatile model. Previous studies typically process multi-task features in a more local way, and thus cannot effectively learn spatially global and cross-task interactions. We propose an Inverted Pyramid multi-task Transformer, capable of modeling cross-task interaction among spatial features of different tasks in a global context.
  arXiv  Detail & Related papers  (2023-06-08T00:28:22Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• Omni-Training for Data-Efficient Deep Learning [80.28715182095975]
  Recent advances reveal that a properly pre-trained model endows an important property: transferability. A tight combination of pre-training and meta-training cannot achieve both kinds of transferability. This motivates the proposed Omni-Training framework towards data-efficient deep learning.
  arXiv  Detail & Related papers  (2021-10-14T16:30:36Z)

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.