相关论文: XFBoost: Improving Text Generation with Controllab…

An interpretable system for open-domain reasoning needs to express its reasoning process in a transparent form. Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a…

Natural Language Generation (NLG) has made great progress in recent years due to the development of deep learning techniques such as pre-trained language models. This advancement has resulted in more fluent, coherent and even properties…

Recent studies show strong generative performance in domain translation especially by using transfer learning techniques on the unconditional generator. However, the control between different domain features using a single model is still…

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…

Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In this paper, we propose Context-Fidelity Boosting (CFB), a…

A Prompt-based Text-To-Speech model allows a user to control different aspects of speech, such as speaking rate and perceived gender, through natural language instruction. Although user-friendly, such approaches are on one hand constrained:…

Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…

Advanced image fusion methods are devoted to generating the fusion results by aggregating the complementary information conveyed by the source images. However, the difference in the source-specific manifestation of the imaged scene content…

To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating…

In recent years, there has been a growing interest in the development of language models capable of generating text with controllable attributes. While several approaches have been proposed, many of these methods require condition-specific…

Recent advances in deep learning research, such as transformers, have bolstered the ability for automated agents to generate creative texts similar to those that a human would write. By default, transformer decoders can only generate new…

This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text…

We propose a novel conditioned text generation model. It draws inspiration from traditional template-based text generation techniques, where the source provides the content (i.e., what to say), and the template influences how to say it.…

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously…

Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language processing, mostly based on the self-attention mechanism.…

Neural text generation models conditioning on given input (e.g. machine translation and image captioning) are usually trained by maximum likelihood estimation of target text. However, the trained models suffer from various types of errors…

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…