Copertina

Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Yangming, Zhu, Shixiang, Shen, Tao, Yu, Zhimiao, Chen, Dengsheng, Chen, Taicai, Yang, Yunfei, Zhou, Juan, Cheng, Chen, Ma, Liang, Wu, Xibin, Yan, Benxuan, Li, Ge, Zhang, Tuoyu, Li, Dan, Liu, Chang, Sun, Zhenbang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
di: Shen, Tao, et al.
Pubblicazione: (2025)

MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
di: Kong, Lingshun, et al.
Pubblicazione: (2026)

SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
di: Zhu, Rui, et al.
Pubblicazione: (2024)

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
di: Chen, Pengtao, et al.
Pubblicazione: (2024)

DiT-HC: Enabling Efficient Training of Visual Generation Model DiT on HPC-oriented CPU Cluster
di: Zhang, Jinxiao, et al.
Pubblicazione: (2026)

DiT4Edit: Diffusion Transformer for Image Editing
di: Feng, Kunyu, et al.
Pubblicazione: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
di: Chen, Lei, et al.
Pubblicazione: (2024)

DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
di: Ma, Teli, et al.
Pubblicazione: (2026)

TetriServe: Efficient DiT Serving for Heterogeneous Image Generation
di: Lu, Runyu, et al.
Pubblicazione: (2025)

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation
di: Chen, Bowen, et al.
Pubblicazione: (2025)

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
di: Li, Yunxin, et al.
Pubblicazione: (2024)

LaVin-DiT: Large Vision Diffusion Transformer
di: Wang, Zhaoqing, et al.
Pubblicazione: (2024)

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
di: Chen, Sixiang, et al.
Pubblicazione: (2025)

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
di: Lyu, Hengye, et al.
Pubblicazione: (2026)

Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts
di: Wu, Haoyuan, et al.
Pubblicazione: (2025)

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
di: Fang, Jiarui, et al.
Pubblicazione: (2024)

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE
di: Liu, Zhenyu, et al.
Pubblicazione: (2025)

FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers
di: Chen, Ruichen, et al.
Pubblicazione: (2025)

BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
di: Ma, Yingjie, et al.
Pubblicazione: (2024)

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
di: Chen, Chen, et al.
Pubblicazione: (2025)

OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
di: Wang, Liujianfu, et al.
Pubblicazione: (2025)

DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training
di: Tan, Xin, et al.
Pubblicazione: (2025)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
di: Tian, Yuchuan, et al.
Pubblicazione: (2024)

DiVE: DiT-based Video Generation with Enhanced Control
di: Jiang, Junpeng, et al.
Pubblicazione: (2024)

DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation
di: Feng, He, et al.
Pubblicazione: (2025)

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
di: He, Xianglong, et al.
Pubblicazione: (2025)

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
di: Li, Zhimin, et al.
Pubblicazione: (2024)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
di: Zhao, Lin, et al.
Pubblicazione: (2026)

MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios
di: Li, Shuhuai, et al.
Pubblicazione: (2026)

UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training
di: Zheng, Size, et al.
Pubblicazione: (2026)

DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
di: Shi, Junqi, et al.
Pubblicazione: (2026)

Retraining-Free Merging of Sparse MoE via Hierarchical Clustering
di: Chen, I-Chun, et al.
Pubblicazione: (2024)

Transforming Higher Education with AI-Powered Video Lectures
di: Zhang, Dengsheng
Pubblicazione: (2025)

TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
di: Xie, Yu, et al.
Pubblicazione: (2025)

TextFlux: An OCR‐Free DiT Model for High‐Fidelity Multilingual Scene Text Synthesis
di: Yu Xie, et al.
Pubblicazione: (2026)

RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild
di: Zhou, Jingkai, et al.
Pubblicazione: (2025)

An Invisible Backdoor Attack Based On Semantic Feature
di: Chen, Yangming
Pubblicazione: (2024)

DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation
di: Zheng, Zihao, et al.
Pubblicazione: (2025)

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
di: Sun, Xibo, et al.
Pubblicazione: (2024)

Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
di: Duan, Yue, et al.
Pubblicazione: (2025)