相关论文: NAST: A Non-Autoregressive Generator with Word Ali…

Transformer-based models have led to significant innovation in classical and practical subjects as varied as speech processing, natural language processing, and computer vision. On top of the Transformer, attention-based end-to-end…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

We present a training-free style-aligned image generation method that leverages a scale-wise autoregressive model. While large-scale text-to-image (T2I) models, particularly diffusion-based methods, have demonstrated impressive generation…

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification…

Formality style transfer (FST) is a task that involves paraphrasing an informal sentence into a formal one without altering its meaning. To address the data-scarcity problem of existing parallel datasets, previous studies tend to adopt a…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Text style transfer (TST) aims to modify the style of a text without altering its original meaning. Large language models (LLMs) demonstrate superior performance across multiple tasks, including TST. However, in zero-shot setups, they tend…

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoregressive factors in…

BatGPT is a large-scale language model designed and trained jointly by Wuhan University and Shanghai Jiao Tong University. It is capable of generating highly natural and fluent text in response to various types of input, including text…

Unsupervised text style transfer aims at training a generative model that can alter the style of the input sentence while preserving its content without using any parallel data. In this paper, we employ powerful pre-trained large language…

We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm. Unlike VAR, which is constrained to class-conditioned synthesis for images up to 256$\times$256, STAR enables text-driven image generation up to…

Most image captioning models are autoregressive, i.e. they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. Recently, non-autoregressive decoding has been proposed in machine…

Style transfer aims to render a content image with the visual characteristics of a reference style while preserving its underlying semantic layout and structural geometry. While recent diffusion-based models demonstrate strong stylization…

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into…

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently.…

Contemporary recommendation systems are designed to meet users' needs by delivering tailored lists of items that align with their specific demands or interests. In a multi-stage recommendation system, reranking plays a crucial role by…

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

While diffusion models have achieved remarkable progress in style transfer tasks, existing methods typically rely on fine-tuning or optimizing pre-trained models during inference, leading to high computational costs and challenges in…