paper-with-me

Papers

Balancing Understanding and Generation in Discrete Diffusion Models

2026-02-01 · Yue Liu, Yuzhong Zhao, Zheyong Xie, Qixiang Ye, Jianbin Jiao, Yao Hu, Shaosheng Cao, Yunfan Liu arxiv

In discrete generative modeling, two dominant paradigms demonstrate divergent capabilities: Masked Diffusion Language Models (MDLM) excel at semantic understanding and zero-shot generalization, whereas Uniform-noise Diffusion Language Models (UDLM) achieve strong few-step generation quality, yet neither attains balanced performance across both dimensions. To address this, we propose XDLM, which bridges the two paradigms via a stationary noise kernel. XDLM offers two key contributions: (1) it provides a principled theoretical unification of MDLM and UDLM, recovering each paradigm as a special case; and (2) an alleviated memory bottleneck enabled by an algebraic simplification of the posterior probabilities. Experiments demonstrate that XDLM advances the Pareto frontier between understanding capability and generation quality. Quantitatively, XDLM surpasses UDLM by 5.4 points on zero-shot text benchmarks and outperforms MDLM in few-step image generation (FID 54.1 vs. 80.8). When scaled to tune an 8B-parameter large language model, XDLM achieves 15.0 MBPP in just 32 steps, effectively doubling the baseline performance. Finally, analysis of training dynamics reveals XDLM's superior potential for long-term scaling. Code is available at https://github.com/MzeroMiko/XDLM

📄 PDF Abstract BibTeX arXiv:2602.01362

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot GeneralizationImage Generation

Similar Papers 제목 키워드 기반

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

2026-03-06 · Lijiang Li, Zuwei Long, Yunhang Shen, Heting Gao 외 arxiv

While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective an…

Image Generation

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

2025-12-16 · Ruishu Zhu, Zhihao Huang, Jiacheng Sun, Ping Luo 외 arxiv

Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view g…

Text-to-Image Generation

Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding

2025-10-07 · Yi Xin, Qi Qin, Siqi Luo, Kaiwen Zhu 외 arxiv

We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modelin…

Text-to-Image GenerationImage InpaintingImage Editing

A Unification of Discrete, Gaussian, and Simplicial Diffusion

2025-12-17 · Nuria Alina Chandra, Yucen Lily Li, Alan N. Amin, Alex Ali 외 arxiv

To model discrete sequences such as DNA, proteins, and language using diffusion, practitioners must choose between three major methods: diffusion in discrete space, Gaussian diffusion in Euclidean space, or diffusion on …

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

2026-03-19 · Yuqing Wang, Chuofan Ma, Zhijie Lin, Yao Teng 외 arxiv

Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal architectures. However, current discret…