Related papers: Hierarchical Resolution Transformers: A Wavelet-In…
Previous studies such as VizWiz find that Visual Question Answering (VQA) systems that can read and reason about text in images are useful in application areas such as assisting visually-impaired people. TextVQA is a VQA dataset geared…
This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm…
This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically demonstrating that hallucination is an inevitable structural limitation. The embedding…
Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…
We present ASSET, a neural architecture for automatically modifying an input high-resolution image according to a user's edits on its semantic segmentation map. Our architecture is based on a transformer with a novel attention mechanism.…
In the field of medical CT image processing, convolutional neural networks (CNNs) have been the dominant technique.Encoder-decoder CNNs utilise locality for efficiency, but they cannot simulate distant pixel interactions properly.Recent…
Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and…
The recent rise of generative artificial intelligence (AI), powered by Transformer networks, has achieved remarkable success in natural language processing, computer vision, and graphics. However, the application of Transformers in…
We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns. The proposed HWT captures the long and…
Large Language Models (LLMs) have ushered in a new wave of artificial intelligence advancements impacting every scientific field and discipline. We live in a world where most of the data around us, e.g., text, audio, and music, has a…
Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be…
Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is…
In accelerated MRI reconstruction, the anatomy of a patient is recovered from a set of under-sampled and noisy measurements. Deep learning approaches have been proven to be successful in solving this ill-posed inverse problem and are…
Obtaining high-resolution hyperspectral images (HR-HSI) is costly and data-intensive, making it necessary to fuse low-resolution hyperspectral images (LR-HSI) with high-resolution RGB images (HR-RGB) for practical applications. However,…
Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as…
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…
The transformer architecture has catalyzed revolutionary advances in language modeling. However, recent architectural recipes, such as state-space models, have bridged the performance gap. Motivated by this, we examine the benefits of…
Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM), a hierarchical extension to the language modeling problem…
The underlying structure of natural language is hierarchical; words combine into phrases, which in turn form clauses. An awareness of this hierarchical structure can aid machine learning models in performing many linguistic tasks. However,…
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural…