Related papers: Diffusion-CAM: Faithful Visual Explanations for dM…

Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have…

Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly…

Diffusion models offer appealing properties for language generation, such as parallel decoding and iterative refinement, but the discrete and highly structured nature of text challenges the direct application of diffusion principles. In…

Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models. These models exhibit a remarkable ability to generate highly artistic and intricately detailed images based on…

Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks, establishing themselves as an alternative to autoregressive large language models (LLMs). Unlike autoregressive LLMs that…

Diffusion models have become the mainstream architecture for text-to-image generation, achieving remarkable progress in visual quality and prompt controllability. However, current inference pipelines generally lack interpretable semantic…

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, diffusion-based language models have emerged as a promising alternative to the autoregressive paradigm,…

Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enable controllable generation without retraining. Recent work…

Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…

Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirectional context modeling, but most existing dMLLMs…

Large language models (LLMs) based on decoder-only transformers have demonstrated superior text understanding capabilities compared to CLIP and T5-series models. However, the paradigm for utilizing current advanced LLMs in text-to-image…

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We…

Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, block-wise KV cache refreshing, cross-step reuse, and a non-GEMM-centric sampling phase. These…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions given as endpoints. Despite their promising performance in tasks like image translation, DDBMs…

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…