Related papers: Enhancing Text Generation with Cooperative Trainin…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…

Although current state-of-the-art language models have achieved impressive results in numerous natural language processing tasks, still they could not solve the problem of producing repetitive, dull and sometimes inconsistent text in…

Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios. The crux is that the number of training samples for Maximum Likelihood Estimation is…

The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective…

As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on autoregressive (AR) generation, producing one token at a time…

End-to-end models for goal-orientated dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vectors. We introduce an approach to learning representations of messages in dialogues by…

Modern language models can generate high-quality short texts. However, they often meander or are incoherent when generating longer texts. These issues arise from the next-token-only language modeling objective. Recent work in…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

Text-driven human motion generation based on diffusion strategies establishes a reliable foundation for multimodal applications in human-computer interactions. However, existing advances face significant efficiency challenges due to the…

Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion…

This article presents a framework for generating optimisation models using a pre-trained generative transformer. The framework involves specifying the features that the optimisation model should have and using a language model to generate…

A generative adversarial network (GAN) has been a representative backbone model in generative artificial intelligence (AI) because of its powerful performance in capturing intricate data-generating processes. However, the GAN training is…

We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both "pointwise" and "distributional" constraints over…

Users interact with text, image, code, or other editors on a daily basis. However, machine learning models are rarely trained in the settings that reflect the interactivity between users and their editor. This is understandable as training…

Generating multiple categories of texts is a challenging task and draws more and more attention. Since generative adversarial nets (GANs) have shown competitive results on general text generation, they are extended for category text…

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…