LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

arXiv:2604.20796v1 Announce Type: new Abstract: We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a MoE-based dLLM backbone, and a diffusion decoder. By discretizing continuous visual inputs via SigLIP-VQ, the model enables block-level masked diffusion for both text and vision inputs within the backbone, while the decoder reconstructs visual tokens into high-fidelity images. Inference efficiency is enhanced beyond parallel decoding through prefix-aware optimizations in the backbone and few-step distillation in the decoder. Supported by carefully curated large-scale data and a tailored multi-stage training pipeline, LLaDA2.0-Uni matches specialized VLMs in multimodal understanding while delivering strong performance in image generation and editing. Its native support for interleaved generation and reasoning establishes a promising and scalable paradigm for next-generation unified foundation models. Codes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.

Related

• Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
• Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
• Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
• BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation

Source: arXiv cs.CV | 2026-04-23