Abstract
LLaDA-o is an omni diffusion model that uses a Mixture of Diffusion framework to jointly handle text understanding and visual generation through a shared attention backbone, achieving state-of-the-art performance in multimodal tasks.
We present LLaDA-o, an effective and length-adaptive omni diffusion model for multimodal understanding and generation. LLaDA-o is built on a Mixture of Diffusion (MoD) framework that decouples discrete masked diffusion for text understanding and continuous diffusion for visual generation, while coupling them through a shared, simple, and efficient attention backbone that reduces redundant computation for fixed conditions. Building on MoD, we further introduce a data-centric length adaptation strategy that enables flexible-length decoding in multimodal settings without architectural changes. Extensive experiments show that LLaDA-o achieves state-of-the-art performance among omni-diffusion models on multimodal understanding and generation benchmarks, and reaches 87.04 on DPG-Bench for text-to-image generation, supporting the effectiveness of unified omni diffusion modeling. Code is available at https://github.com/ML-GSAI/LLaDA-o.
Community
We present LLaDA-o, a length-adaptive MoD omni-diffusion model that unifies multimodal understanding and image generation, reaching 87.04 on DPG-Bench; we will open-source the model and code in https://github.com/ML-GSAI/LLaDA-o.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026)
- Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding (2026)
- VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding (2026)
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders (2026)
- VocalNet-MDM: Accelerating Streaming Speech LLM via Self-Distilled Masked Diffusion Modeling (2026)
- Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing (2026)
- NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper