Related papers: Ctrl-U: Robust Conditional Image Generation via Un…

Reward models are critical for improving large language models (LLMs), particularly in reinforcement learning from human feedback (RLHF) or inference-time verification. Current reward modeling typically relies on scores of overall responses…

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications. A well-calibrated model should be accurate when it is certain about its prediction and indicate…

Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks…

Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor-…

Quantifying uncertainty of predictions has been identified as one way to develop more trustworthy artificial intelligence (AI) models beyond conventional reporting of performance metrics. When considering their role in a clinical decision…

This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge remains that…

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background…

Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in the training dataset, we often are more concerned with other…

Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In…

Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…

Recent approaches in personalized reward modeling have primarily focused on leveraging user interaction history to align model judgments with individual preferences. However, existing approaches largely treat user context as a static or…

Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone…

The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We address this need by presenting a novel approach based on…

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some…

Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This paradigm overlooks the intrinsic uncertainty of low-agreement…

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…