Related papers: Few-shot Compositional Font Generation with Dual M…
As a precious part of the human cultural heritage, Chinese poetry has influenced people for generations. Automatic poetry composition is a challenge for AI. In recent years, significant progress has been made in this area benefiting from…
Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain…
The metaverse consists of hardware, software, and content, among which text design plays a critical role in enhancing user immersion and usability as a content element. However, in languages such as Korean and Chinese that require thousands…
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment. Quantization emerges as one of the most effective…
Research has shown that sequence-to-sequence neural models, particularly those with the attention mechanism, can successfully generate classical Chinese poems. However, neural models are not capable of generating poems that match specific…
Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream…
Compositional generalization tests are often used to estimate the compositionality of LLMs. However, such tests have the following limitations: (1) they only focus on the output results without considering LLMs' understanding of sample…
We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…
In the second part of the series papers, we set out to study the algorithmic efficiency of sparse sensing. Stemmed from co-prime sensing, we propose a generalized framework, termed Diophantine sensing, which utilizes generic Diophantine…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…
As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems. The problem is difficult, as these are large,…
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…
In this paper, we describe methods for handling multilingual non-compositional constructions in the framework of GF. We specifically look at methods to detect and extract non-compositional phrases from parallel texts and propose methods to…
This work introduces (1) a technique that allows large language models (LLMs) to leverage user-provided code when solving programming tasks and (2) a method to iteratively generate modular sub-functions that can aid future code generation…
Computer poetry generation is our first step towards computer writing. Writing must have a theme. The current approaches of using sequence-to-sequence models with attention often produce non-thematic poems. We present a novel conditional…
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in…
Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex…
To solve a new task from minimal experience, it is essential to effectively reuse knowledge from previous tasks, a problem known as meta-learning. Compositional solutions, where common elements of computation are flexibly recombined into…
We present a new scalable, lightweight algorithm to incrementally construct the BWT and FM-index of large string sets such as those produced by Next Generation Sequencing. The algorithm is designed for massive parallelism and can…
In recent years, distinctive-dictionary construction has gained importance due to his usefulness in data processing. Usually, one or more dictionaries are constructed from a training data and then they are used to classify signals that did…