Cover Image

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Lijiang, Long, Zuwei, Shen, Yunhang, Gao, Heting, Cao, Haoyu, Sun, Xing, Shan, Caifeng, He, Ran, Fu, Chaoyou
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VITA: Towards Open-Source Interactive Omni Multimodal LLM
by: Fu, Chaoyou, et al.
Published: (2024)

VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
by: Long, Zuwei, et al.
Published: (2025)

DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE
by: Shao, Hang, et al.
Published: (2025)

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
by: Fu, Chaoyou, et al.
Published: (2025)

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding
by: Yang, Ruoliu, et al.
Published: (2026)

LUCY: Linguistic Understanding and Control Yielding Early Stage of Her
by: Gao, Heting, et al.
Published: (2025)

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
by: Wang, Xiong, et al.
Published: (2024)

Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?
by: Jiang, Hongbo, et al.
Published: (2026)

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
by: Fu, Chaoyou, et al.
Published: (2023)

PersonaVLM: Long-Term Personalized Multimodal LLMs
by: Nie, Chang, et al.
Published: (2026)

VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
by: Dong, Shaoqi, et al.
Published: (2025)

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
by: Fu, Chaoyou, et al.
Published: (2026)

Cantor: Inspiring Multimodal Chain-of-Thought of MLLM
by: Gao, Timin, et al.
Published: (2024)

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy
by: Shen, Yunhang, et al.
Published: (2025)

VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
by: Liu, Xiaoyu, et al.
Published: (2025)

Unified Multimodal Discrete Diffusion
by: Swerdlow, Alexander, et al.
Published: (2025)

MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs
by: Fu, Chaoyou, et al.
Published: (2024)

Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
by: Li, Shufan, et al.
Published: (2025)

SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
by: Liu, Ruohan, et al.
Published: (2026)

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation
by: Xiao, Yicheng, et al.
Published: (2025)

OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding
by: Xi, Dianbing, et al.
Published: (2025)

Woodpecker: Hallucination Correction for Multimodal Large Language Models
by: Yin, Shukang, et al.
Published: (2023)

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models
by: Xie, Wulin, et al.
Published: (2025)

Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation
by: Zhou, Zhiwang, et al.
Published: (2025)

Omni-Referring Image Segmentation
by: Zheng, Qiancheng, et al.
Published: (2025)

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
by: Mao, Jiawei, et al.
Published: (2025)

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
by: Liu, Runtao, et al.
Published: (2024)

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
by: Gao, Yisen, et al.
Published: (2025)

MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models
by: He, Haoyu, et al.
Published: (2025)

VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
by: Zhou, Chenyu, et al.
Published: (2024)

Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction
by: Gao, Yisen, et al.
Published: (2025)

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
by: Li, Zhe, et al.
Published: (2025)

Simplified and Generalized Masked Diffusion for Discrete Data
by: Shi, Jiaxin, et al.
Published: (2024)

Balancing Understanding and Generation in Discrete Diffusion Models
by: Liu, Yue, et al.
Published: (2026)

OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework
by: Zeng, Weixuan, et al.
Published: (2026)

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

Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion
by: Lu, Yizhuo, et al.
Published: (2026)

Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes
by: Li, Bocheng, et al.
Published: (2025)

Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
by: Chao, Chen-Hao, et al.
Published: (2025)

Ming-Omni: A Unified Multimodal Model for Perception and Generation
by: AI, Inclusion, et al.
Published: (2025)