中文
相关论文

相关论文: The troublesome kernel -- On hallucinations, no fr…

200 篇论文

Large Language Models (LLMs) are increasingly applied to medical imaging tasks, including image interpretation and synthetic image generation. However, these models often produce hallucinations, which are confident but incorrect outputs…

图像与视频处理 · 电气工程与系统科学 2025-08-12 Anindya Bijoy Das , Shahnewaz Karim Sakib , Shibbir Ahmed

AI-based image reconstruction models are increasingly deployed in clinical workflows to improve image quality from noisy data, such as low-dose X-rays or accelerated MRI scans. However, these models are typically evaluated using pixel-level…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Matteo Wohlrapp , Niklas Bubeck , Daniel Rueckert , William Lotter

The No Free Lunch theorems prove that under a uniform distribution over induction problems (search problems or learning problems), all induction algorithms perform equally. As I discuss in this chapter, the importance of the theorems arises…

机器学习 · 计算机科学 2020-07-22 David H. Wolpert

Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Tayyab Nasir , Daochang Liu , Ajmal Mian

No-reference image quality assessment (NR-IQA) is a fundamental yet challenging task in low-level computer vision community. The difficulty is particularly pronounced for the limited information, for which the corresponding reference for…

计算机视觉与模式识别 · 计算机科学 2018-04-06 Kwan-Yee Lin , Guanxiang Wang

Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund…

Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically deviates from rationality, several approaches have been tried to account for specific human…

人工智能 · 计算机科学 2019-01-14 Stuart Armstrong , Sören Mindermann

Recent advances in image generation models (IGMs), particularly diffusion-based architectures such as Stable Diffusion (SD), have markedly enhanced the quality and diversity of AI-generated visual content. However, their generative…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Renyang Liu , Guanlin Li , Tianwei Zhang , See-Kiong Ng

This paper provides an overview of current approaches for solving inverse problems in imaging using variational methods and machine learning. A special focus lies on point estimators and their robustness against adversarial perturbations.…

图像与视频处理 · 电气工程与系统科学 2024-07-10 Alexander Auras , Kanchana Vaishnavi Gandikota , Hannah Droege , Michael Moeller

In recent years, deep learning has achieved remarkable empirical success for image reconstruction. This has catalyzed an ongoing quest for precise characterization of correctness and reliability of data-driven methods in critical use-cases,…

计算机视觉与模式识别 · 计算机科学 2022-09-15 Subhadip Mukherjee , Andreas Hauptmann , Ozan Öktem , Marcelo Pereyra , Carola-Bibiane Schönlieb

Inverse problems consist in reconstructing signals from incomplete sets of measurements and their performance is highly dependent on the quality of the prior knowledge encoded via regularization. While traditional approaches focus on…

图像与视频处理 · 电气工程与系统科学 2022-07-04 Antonio Montanaro , Diego Valsesia , Enrico Magli

Large language models (LLMs) have achieved a degree of success in generating coherent and contextually relevant text, yet they remain prone to a significant challenge known as hallucination: producing information that is not substantiated…

计算与语言 · 计算机科学 2024-10-28 Ray Li , Tanishka Bagade , Kevin Martinez , Flora Yasmin , Grant Ayala , Michael Lam , Kevin Zhu

In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead…

人工智能 · 计算机科学 2023-06-07 Anirban Mukherjee , Hannah Chang

Hallucination, one kind of pathological translations that bothers Neural Machine Translation, has recently drawn much attention. In simple terms, hallucinated translations are fluent sentences but barely related to source inputs. Arguably,…

计算与语言 · 计算机科学 2022-06-28 Jianhao Yan , Fandong Meng , Jie Zhou

Image manipulation detection algorithms designed to identify local anomalies often rely on the manipulated regions being ``sufficiently'' different from the rest of the non-tampered regions in the image. However, such anomalies might not be…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Rosaura G. VidalMata , Priscila Saboia , Daniel Moreira , Grant Jensen , Jason Schlessman , Walter J. Scheirer

Inverse problems in imaging are typically ill-posed and are usually solved by employing regularized optimization techniques. The usage of appropriate constraints can restrict the solution space, thus making it feasible for a reconstruction…

图像与视频处理 · 电气工程与系统科学 2025-11-14 Jasleen Birdi , Tamal Majumder , Debanjan Halder , Muskan Kularia , Kedar Khare

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user…

计算机视觉与模式识别 · 计算机科学 2016-10-06 Richard Zhang , Phillip Isola , Alexei A. Efros

Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with…

计算机视觉与模式识别 · 计算机科学 2024-03-13 Qidong Huang , Xiaoyi Dong , Pan Zhang , Bin Wang , Conghui He , Jiaqi Wang , Dahua Lin , Weiming Zhang , Nenghai Yu

We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…

人工智能 · 计算机科学 2025-11-20 Aran Nayebi

We present and analyse an approach to image reconstruction problems with imperfect forward models based on partially ordered spaces - Banach lattices. In this approach, errors in the data and in the forward models are described using order…

数值分析 · 计算机科学 2018-08-15 Yury Korolev , Jan Lellmann