Related papers: Sampling and Ranking for Digital Ink Generation on…
In the online advertising industry, the process of designing an ad creative (i.e., ad text and image) requires manual labor. Typically, each advertiser launches multiple creatives via online A/B tests to infer effective creatives for the…
The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…
Handwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion…
Large language models show great potential in generating and optimizing code. Widely used sampling methods such as Nucleus Sampling increase the diversity of generation but often produce repeated samples for low temperatures and incoherent…
Building on the remarkable achievements in generative sampling of natural images, we propose an innovative challenge, potentially overly ambitious, which involves generating samples of entire multivariate time series that resemble images.…
Robot calligraphy is an emerging exploration of artificial intelligence in the fields of art and education. Traditional calligraphy generation researches mainly focus on methods such as tool-based image processing, generative models, and…
Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…
Recognizing handwriting images is challenging due to the vast variation in writing style across many people and distinct linguistic aspects of writing languages. In Vietnamese, besides the modern Latin characters, there are accent and…
Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate this issue, various modifications to a model's sampling…
In most of neural machine translation distillation or stealing scenarios, the goal is to preserve the performance of the target model (teacher). The highest-scoring hypothesis of the teacher model is commonly used to train a new model…
The aim of this thesis is to determine classes of NP relations for which random generation and approximate counting problems admit an efficient solution. Since efficient rank implies efficient random generation, we first investigate some…
In this paper, we address the problem of generative dataset distillation that utilizes generative models to synthesize images. The generator may produce any number of images under a preserved evaluation time. In this work, we leverage the…
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and…
In practice, machine learning experts are often confronted with imbalanced data. Without accounting for the imbalance, common classifiers perform poorly and standard evaluation metrics mislead the practitioners on the model's performance. A…
Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…
Despite the prominence of neural abstractive summarization models, we know little about how they actually form summaries and how to understand where their decisions come from. We propose a two-step method to interpret summarization model…
Our research introduces an innovative Natural Language Generation (NLG) approach that aims to optimize user experience and alleviate the workload of human customer support agents. Our primary objective is to generate informal summaries for…
Large Language Models (LLMs) can exhibit considerable variation in the quality of their sampled outputs. Reranking and selecting the best generation from the sampled set is a popular way of obtaining strong gains in generation quality. In…
Synthetic Data Generation (SDG), leveraging Large Language Models (LLMs), has recently been recognized and broadly adopted as an effective approach to improve the performance of smaller but more resource and compute efficient LLMs through…
We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two…