Related papers: Return of Unconditional Generation: A Self-supervi…

Image generation with explicit condition or label generally works better than unconditional methods. In modern GAN frameworks, both generator and discriminator are formulated to model the conditional distribution of images given with…

We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data and (ii) unlabeled data with samples belonging to one of…

Image generation abilities of text-to-image diffusion models have significantly advanced, yielding highly photo-realistic images from descriptive text and increasing the viability of leveraging synthetic images to train computer vision…

Classifier-free guidance (CFG) has become a widely adopted and practical approach for enhancing generation quality and improving condition alignment. Recent studies have explored guidance mechanisms for unconditional generation, yet these…

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…

Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data.…

The task of image captioning aims to generate captions directly from images via the automatically learned cross-modal generator. To build a well-performing generator, existing approaches usually need a large number of described images,…

Developing models that are capable of answering questions of the form "How would x change if y had been z?'" is fundamental to advancing medical image analysis. Training causal generative models that address such counterfactual questions,…

Determining conditional independence (CI) relationships between random variables is a fundamental yet challenging task in machine learning and statistics, especially in high-dimensional settings. Existing generative model-based CI testing…

The lack of domain-specific data in the pre-training of Large Language Models (LLMs) severely limits LLM-based decision systems in specialized applications, while post-training a model in the scenarios requires significant computational…

Controllable generation using StyleGANs is usually achieved by training the model using labeled data. For audio textures, however, there is currently a lack of large semantically labeled datasets. Therefore, to control generation, we…

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it…

Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…

Conditional image generation models have achieved remarkable results by leveraging text-based control to generate customized images. However, the high resource demands of these models and the scarcity of well-annotated data have hindered…

While representation alignment with self-supervised models has been shown to improve diffusion model training, its potential for enhancing inference-time conditioning remains largely unexplored. We introduce Representation-Aligned Guidance…

Retrieval-augmented generation (RAG) is widely used to augment large language models (LLMs) with external knowledge. However, many benchmark datasets, designed to test RAG performance, comprise many questions that can already be answered…

The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works employed…

This paper proposes a series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis and we name the proposed model as ArtGAN. One of the key innovation of ArtGAN is that, the gradient of the loss…

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, tabular data suffers from class imbalance, a problem that causes serious performance…