arXiv Computer Vision September 2, 2026 By Penghao Wu, Haiwen Diao, Weichen Fan, Lewei Lu, Dahua Lin, Ziwei Liu

Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System

Read the original on arXiv Computer Vision →

The paper investigates how visual understanding and generation objectives interact within unified multimodal models (UMMs). At the representation level, each objective enriches the other, but forcing them through the same computation path can cause one to dominate; a task‑decoupled architecture mitigates this. At the task and system levels, the authors demonstrate bidirectional transfer between shared knowledge and superior performance of an end‑to‑end UMM over a planner–executor pipeline on complex tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Machine Learning

Aug 6

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

arXiv:2608. 05000v1 Announce Type: cross Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining.

By Junlin Han, Shengbang Tong, David Fan, Minghao Chen, Philip Torr, Filippos Kokkinos, Mike Lewis

nlp multimodal safety

arXiv AI

Jul 7

Transferability Between Understanding and Generation in Unified Multimodal Models

arXiv:2607. 04423v1 Announce Type: cross Abstract: Unified Multimodal Models (UMMs) integrate image understanding and generation within a single architecture, yet how the two tasks interact remains understudied.

By Jiwon Kang, Heeji Yoon, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong Kim

llms fine-tuning multimodal

arXiv AI

Sep 7

Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study

The study investigates how unified vision‑language models (VLMs) can simultaneously support visual understanding and generation. Using controlled benchmarks (SmartWatch and modified CelebA) that pair VQA, captioning, and text‑to‑image tasks, the authors evaluate several LLM‑based architectures built on SigLIP and VQ‑VAE visual spaces. Results show that mixed training can improve both understanding and generation, but the gains depend on how well the visual input and output spaces are aligned; misaligned or distorted visual spaces can weaken or reverse these benefits. The paper also demonstrates that balancing data across tasks and controlling attribute frequencies can help recover underrepresented visual concepts, and that the transfer is driven more by the base language model’s learned relationships than by visual adapters.

By Jihai Zhang, Tianle Li, Linjie Li, Zhengyuan Yang, Yu Cheng

llms diffusion multimodal benchmarks

arXiv Machine Learning

Jun 30

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

arXiv:2604. 07753v2 Announce Type: replace-cross Abstract: Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts.

By Xiangyue Liu, Zijian Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Ping Tan

llms diffusion multimodal benchmarks

Hugging Face Trending Papers

Jul 5

Transferability Between Understanding and Generation in Unified Multimodal Models

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.

llms fine-tuning multimodal

arXiv AI

Jun 3

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models

arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.

By Xinpeng Dong, Min Zhang, Kairong Han, Xu Tan, Fei Wu, Kun Kuang

llms computer-vision multimodal benchmarks safety

One email a morning, machine-written

Related stories

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Transferability Between Understanding and Generation in Unified Multimodal Models

Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

Transferability Between Understanding and Generation in Unified Multimodal Models

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models