Related papers: Conditional [MASK] Discrete Diffusion Language Mod…

As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeable blurriness. This issue stems from the unrealistic…

While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple masked discrete…

Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative…

We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regression function using the noise-outsourcing lemma. The proposed…

Acoustic echo and background noise pose challenges on speech enhancement in hands-free systems and speakerphones. Discriminatively trained end-to-end methods represent a powerful solution for joint acoustic echo control (AEC) and denoising.…

Diffusion models typically generate data through a fixed denoising trajectory that is shared across all samples. However, generation targets can differ in complexity, suggesting that a single pre-defined diffusion process may not be optimal…

Denoising diffusion models have gained popularity as a generative modeling technique for producing high-quality and diverse images. Applying these models to downstream tasks requires conditioning, which can take the form of text, class…

The modern autoregressive Large Language Models (LLMs) have achieved outstanding performance on NLP benchmarks, and they are deployed in the real world. However, they still suffer from limitations of the autoregressive training paradigm.…

We tackle the problem of generating audio samples conditioned on descriptive text captions. In this work, we propose AaudioGen, an auto-regressive generative model that generates audio samples conditioned on text inputs. AudioGen operates…

Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic…

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire. This paper describes Diffusion-Decoding models with Contrastive representations…

Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to predict the quantized…

Discrete diffusion models (DDMs) are a powerful class of generative models for categorical data, but they typically require many function evaluations for a single sample, making inference expensive. Existing acceleration methods either rely…

Current large-scale auto-regressive language models display impressive fluency and can generate convincing text. In this work we start by asking the question: Can the generations of these models be reliably distinguished from real text by…

Diffusion probabilistic models (DPMs) have shown remarkable results on various image synthesis tasks such as text-to-image generation and image inpainting. However, compared to other generative methods like VAEs and GANs, DPMs lack a…

Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex,…

Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…

Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural…

Current text recognition systems, including those for handwritten scripts and scene text, have relied heavily on image synthesis and augmentation, since it is difficult to realize real-world complexity and diversity through collecting and…

While diffusion models excel at conditional generating high-quality images, prior works in discrete diffusion models were not evaluated on conditional long-text generation. In this work, we address the limitations of prior discrete…