Related papers: MDM-Prime-v2: Binary Encoding and Index Shuffling …

Denoising Diffusion Models (DDMs) have become a popular tool for generating high-quality samples from complex data distributions. These models are able to capture sophisticated patterns and structures in the data, and can generate samples…

State-of-the-art language models are autoregressive and operate on subword units known as tokens. Specifically, one must encode the conditioning string into a list of tokens before passing to the language models for next-token prediction.…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…

While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework…

Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While there have been advancements in diffusion models, their…

In the realm of self-supervised learning (SSL), masked image modeling (MIM) has gained popularity alongside contrastive learning methods. MIM involves reconstructing masked regions of input images using their unmasked portions. A notable…

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of…

Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space models) due to its efficient handling of long-range…

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

In this work, we address the challenge of multi-domain translation, where the objective is to learn mappings between arbitrary configurations of domains within a defined set (such as $(D_1, D_2)\rightarrow{}D_3$, $D_2\rightarrow{}(D_1,…

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats generated tokens as immutable, which may lead to error…

Masked diffusion models (MDMs) offer a compelling alternative to autoregressive models (ARMs) for discrete text generation because they enable parallel token sampling, rather than sequential, left-to-right generation. This means potentially…

Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. Standard DMs can be viewed as an instantiation of hierarchical variational autoencoders (VAEs) where the latent variables are inferred…

Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet such flexibility introduces a critical challenge: inference…

The development of deep neural networks is witnessing fast growth in network size, which requires novel hardware computing platforms with large bandwidth and low energy consumption. Optical computing has been a potential candidate for…

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…

While foundation models demonstrate impressive performance across various tasks, they remain vulnerable to adversarial inputs. Current research explores various approaches to enhance model robustness, with Diffusion Denoised Smoothing…

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc…

We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models when trained in a federated setting, presenting the specific…

We present T$^\star$, a simple TraceRL-based training curriculum for progressive block-size scaling in masked diffusion language models (MDMs). Starting from an AR-initialized small-block MDM, T$^\star$ transitions smoothly to larger…