Related papers: An Invariant Learning Characterization of Controll…
Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation. Yet, while current methods are capable of producing a coherent text which is several hundred words long, attaining…
Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, covers, cartoons, etc.), the text in natural scene images…
Textual image generation spans diverse fields like advertising, education, product packaging, social media, information visualization, and branding. Despite recent strides in language-guided image synthesis using diffusion models, current…
Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…
Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
We study the problem of controllable generation of long-term sequential behaviors, where the goal is to calibrate to multiple behavior styles simultaneously. In contrast to the well-studied areas of controllable generation of images, text,…
In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically,…
Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…
The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last ten years, due to the increased availability of documents in digital form and the ensuing need to organize…
Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take…
Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…
Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…
To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight framework for…
Many applications require categorization of text documents using predefined categories. The main approach to performing text categorization is learning from labeled examples. For many tasks, it may be difficult to find examples in one…
While text-to-image diffusion models can generate highquality images from textual descriptions, they generally lack fine-grained control over the visual composition of the generated images. Some recent works tackle this problem by training…
While large language models (LLMs) have achieved impressive performance in generating fluent and realistic text, controlling the generated text so that it exhibits properties such as safety, factuality, and non-toxicity remains challenging.…
Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG). However, vanilla prompt tuning tends to imitate training corpus characteristics beyond the control…
Controllable image generation has always been one of the core demands in image generation, aiming to create images that are both creative and logical while satisfying additional specified conditions. In the post-AIGC era, controllable…
Artistic text generation aims to amplify the aesthetic qualities of text while maintaining readability. It can make the text more attractive and better convey its expression, thus enjoying a wide range of application scenarios such as…