Related papers: Hallucination Index: An Image Quality Metric for G…
Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information. However, previous face hallucination approaches largely ignore facial…
Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact…
Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many task- and domain-specific metrics have been proposed to…
Real-world image denoising is an extremely important image processing problem, which aims to recover clean images from noisy images captured in natural environments. In recent years, diffusion models have achieved very promising results in…
Ultrasound-modulated optical tomography is an emerging biomedical imaging modality which uses the spatially localised acoustically-driven modulation of coherent light as a probe of the structure and optical properties of biological tissues.…
Uncertainty quantification in inverse medical imaging tasks with deep learning has received little attention. However, deep models trained on large data sets tend to hallucinate and create artifacts in the reconstructed output that are not…
Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-augmented generation, and agentic interaction. This…
This paper discusses the challenges of evaluating deblurring-methods quality and proposes a reduced-reference metric based on machine learning. Traditional quality-assessment metrics such as PSNR and SSIM are common for this task, but not…
The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…
There is an increasing interest in using image-generating diffusion models for deep data augmentation and image morphing. In this context, it is useful to interpolate between latents produced by inverting a set of input images, in order to…
Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and…
Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content, achieving state-of-the-art performance across various vision-language tasks. However, these models often generate…
Denoising diffusion models (DDMs) have recently attracted increasing attention by showing impressive synthesis quality. DDMs are built on a diffusion process that pushes data to the noise distribution and the models learn to denoise. In…
Large language models are increasingly being used in patient-facing medical question answering, where hallucinated outputs can vary widely in potential harm. However, existing hallucination standards and evaluation metrics focus primarily…
Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder…
Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise…
Large Language Models (LLMs) have succeeded in a variety of natural language processing tasks [Zha+25]. However, they have notable limitations. LLMs tend to generate hallucinations, a seemingly plausible yet factually unsupported output…
Hallucination in text summarization refers to the phenomenon where the model generates information that is not supported by the input source document. Hallucination poses significant obstacles to the accuracy and reliability of the…
Retrieval-Augmented Generation (RAG) systems remain susceptible to hallucinations despite grounding in retrieved evidence. While current detection methods leverage embedding similarity and natural language inference (NLI), their reliability…
We present a new method for real- and complex-valued image reconstruction from two intensity measurements made in the Fourier plane: the Fourier magnitude of the unknown image, and the intensity of the interference pattern arising from…