Related papers: TextBox: A Unified, Modularized, and Extensible Fr…
Recent large language models (LLMs) achieve impressive performance in source-conditioned text generation but often fail to correctly provide fine-grained attributions for their outputs, undermining verifiability and trust. Moreover,…
Large language models (LLMs) have unified diverse linguistic tasks within a single framework, yet such unification remains unexplored in human motion generation. Existing methods are confined to isolated tasks, limiting flexibility for…
Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and…
An application's user documentation, also referred to as the user manual, is one of the core elements required in application distribution. While there exist many tools to aid an application's developer in creating and maintaining…
We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each…
With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such methods. In this work, we focus on explainable AI and propose a…
Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have shown promise in code understanding, their type inference capabilities remain underexplored. We…
Language models trained with a fixed vocabulary struggle to generalize to novel or out-of-vocabulary words, limiting their flexibility in handling diverse token combinations. Existing dynamic vocabulary approaches attempt to address this…
Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models. In this paper, we introduce new features in Captum…
NLP Workbench is a web-based platform for text mining that allows non-expert users to obtain semantic understanding of large-scale corpora using state-of-the-art text mining models. The platform is built upon latest pre-trained models and…
In recent years, deep generative models have attracted increasing interest due to their capacity to model complex distributions. Among those models, variational autoencoders have gained popularity as they have proven both to be…
In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms, also known as…
Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods…
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…
TensorX is a Python library for prototyping, design, and deployment of complex neural network models in TensorFlow. A special emphasis is put on ease of use, performance, and API consistency. It aims to make available high-level components…
Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets,…
AI-assisted graphic design has emerged as a powerful tool for automating the creation and editing of design elements such as posters, banners, and advertisements. While diffusion-based text-to-image models have demonstrated strong…
Frontier language model quality increasingly hinges on our ability to organize web-scale text corpora for training. Today's dominant tools trade off speed and flexibility: lexical classifiers (e.g., FastText) are fast but limited to…
Existing handwritten text generation methods primarily focus on isolated words. However, realistic handwritten text demands attention not only to individual words but also to the relationships between them, such as vertical alignment and…