Recently, continuous diffusion models (CDM) have been introduced into non-autoregressive
(NAR) text-to-text generation. However, the discrete nature of text increases the difficulty of …

Diffusion-based language models (LMs) have been shown to be competent generative
models that are easy to control at inference and are a promising alternative to …

Diffusion models have gained prominence in generating high-quality sequences of text.
Nevertheless, current approaches predominantly represent discrete text within a continuous …

Diffusion models are a promising tool for high-quality text generation. However, current
models face multiple drawbacks including slow sampling, noise schedule sensitivity, and …

Generative retrieval, which maps from a query to its relevant document identifiers (docids),
has recently emerged as a new information retrieval (IR) paradigm, however, having …

Sequence Labeling (SL) is long-standing in Natural Language Processing (NLP).
Traditionally, discriminative models have been widely used to capture the conditional …

There are rich opportunities to reduce the language complexity of professional content
(either human-written or computer-generated) and make it accessible to a broad audience …

Abstract Domain adaptation is widely employed in cross-domain sentiment analysis,
enabling the transfer of models from label-rich source domains to target domain with fewer …

The diffusion model, a new generative modeling paradigm, has achieved significant success
in generating images, audio, video, and text. It has been adapted for sequence-to-sequence …

This study addresses the discrepancy between training and inference in discrete diffusion
models for text generation. We propose two novel strategies:(1) a training schema that …