Copertina

AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zheng, Dian, Zhang, Manyuan, Li, Hongyu, Zou, Kai, Liu, Hongbo, Guo, Ziyu, Feng, Kaituo, Liu, Yexin, Luo, Ying, Li, Hongsheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
di: Zheng, Dian, et al.
Pubblicazione: (2026)

EditThinker: Unlocking Iterative Reasoning for Any Image Editor
di: Li, Hongyu, et al.
Pubblicazione: (2025)

Gen-Searcher: Reinforcing Agentic Search for Image Generation
di: Feng, Kaituo, et al.
Pubblicazione: (2026)

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding
di: Zou, Kai, et al.
Pubblicazione: (2026)

OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
di: Liu, Yexin, et al.
Pubblicazione: (2025)

Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
di: Zou, Kai, et al.
Pubblicazione: (2025)

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
di: Zou, Kai, et al.
Pubblicazione: (2026)

OneThinker: All-in-one Reasoning Model for Image and Video
di: Feng, Kaituo, et al.
Pubblicazione: (2025)

CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
di: Chen, Zeyu, et al.
Pubblicazione: (2026)

Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation
di: Xu, Lijian, et al.
Pubblicazione: (2023)

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
di: Chen, Shuang, et al.
Pubblicazione: (2026)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
di: Wu, Chengyue, et al.
Pubblicazione: (2024)

Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
di: Liu, Xianjie, et al.
Pubblicazione: (2025)

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction
di: AI, Inclusion, et al.
Pubblicazione: (2025)

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
di: Duan, Chengqi, et al.
Pubblicazione: (2025)

Rethinking Cell Counting Methods: Decoupling Counting and Localization
di: Zheng, Zixuan, et al.
Pubblicazione: (2025)

Rethinking VLM Representation for VLA Initialization
di: Lin, Weifeng, et al.
Pubblicazione: (2026)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
di: Liu, Yexin, et al.
Pubblicazione: (2025)

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
di: Wu, Xiaoshi, et al.
Pubblicazione: (2024)

Rethinking Normalization Strategies and Convolutional Kernels for Multimodal Image Fusion
di: He, Dan, et al.
Pubblicazione: (2024)

AdaTooler-V: Adaptive Tool-Use for Images and Videos
di: Wang, Chaoyang, et al.
Pubblicazione: (2025)

Rethinking Early-Fusion Strategies for Improved Multimodal Image Segmentation
di: Shen, Zhengwen, et al.
Pubblicazione: (2025)

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
di: Tian, Changyao, et al.
Pubblicazione: (2025)

AutoWeather4D: Autonomous Driving Video Weather Conversion via G-Buffer Dual-Pass Editing
di: Liu, Tianyu, et al.
Pubblicazione: (2026)

GLID: Pre-training a Generalist Encoder-Decoder Vision Model
di: Liu, Jihao, et al.
Pubblicazione: (2024)

Unified Multimodal Understanding via Byte-Pair Visual Encoding
di: Zhang, Wanpeng, et al.
Pubblicazione: (2025)

PIDNet: Progressive Implicit Decouple Network for Multimodal Action Quality Assessment
di: Li, Qiqi, et al.
Pubblicazione: (2026)

MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing
di: Hou, Ruibing, et al.
Pubblicazione: (2025)

Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling
di: Wei, Yipan, et al.
Pubblicazione: (2025)

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
di: Liu, Dongyang, et al.
Pubblicazione: (2025)

Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation
di: Lin, Ziyue, et al.
Pubblicazione: (2026)

Temporal Adaptive RGBT Tracking with Modality Prompt
di: Wang, Hongyu, et al.
Pubblicazione: (2024)

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding
di: Hu, Yuxuan, et al.
Pubblicazione: (2025)

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
di: AI, Inclusion, et al.
Pubblicazione: (2025)

GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation
di: Zhang, Weiming, et al.
Pubblicazione: (2024)

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation
di: Zhang, Weiming, et al.
Pubblicazione: (2024)

Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective
di: Zheng, Bowen, et al.
Pubblicazione: (2025)