arXiv Machine Learning June 30, 2026 By Xiangyue Liu, Zijian Zhang, Miles Yang, Zhao Zhong, Liefeng Bo, Ping Tan

Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

arXiv Machine Learning

Jul 2

Rosetta: Composable Native Multimodal Pretraining

arXiv:2607. 00293v1 Announce Type: cross Abstract: Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge.

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

llms diffusion multimodal

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

Jun 26

Semantic Generative Tuning for Unified Multimodal Models

arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.

By Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

computer-vision multimodal benchmarks

arXiv Computer Vision

Sep 2

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

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.

By Penghao Wu, Haiwen Diao, Weichen Fan, Lewei Lu, Dahua Lin, Ziwei Liu

multimodal safety

arXiv AI

Jun 8

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

arXiv:2605. 05225v3 Announce Type: replace-cross Abstract: Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP) inference due to the straggler effect.

By Bo Li, Chuan Wu, Shaolin Zhu

llms multimodal benchmarks

arXiv Computer Vision

2d ago

Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation

The paper investigates whether the sparsity of Mixture-of-Experts (MoE) models leads to intrinsic semantic organization across modalities and domains. It shows that experts naturally specialize semantically even without explicit modular training. The authors propose ExpertLens, a data‑free method that decodes router weights to identify domain‑specialized experts, enabling selective fine‑tuning that matches or exceeds full fine‑tuning while updating only 21.7–47.0% of parameters and achieving a 4.0× speedup, outperforming LoRA in both performance and efficiency.

By Damiano Marsili, Raphi Kang, Aditya Mehta, Pietro Perona, Georgia Gkioxari

fine-tuning efficiency multimodal