相关论文: Low to High Dimensional Modality Hallucination usi…

Hallucinations are an inescapable consequence of solving inverse problems with deep neural networks. The expressiveness of recent generative models is the reason why they can yield results far superior to conventional regularizers; it can…

Multi-modality images have been widely used and provide comprehensive information for medical image analysis. However, acquiring all modalities among all institutes is costly and often impossible in clinical settings. To leverage more…

Large-scale vision-language models have demonstrated impressive skill in handling tasks that involve both areas. Nevertheless, these models frequently experience significant issues with generating inaccurate information, which is…

Tomographic image reconstruction is generally an ill-posed linear inverse problem. Such ill-posed inverse problems are typically regularized using prior knowledge of the sought-after object property. Recently, deep neural networks have been…

Autonomous systems are soon to be ubiquitous, spanning manufacturing, agriculture, healthcare, entertainment, and other industries. Most of these systems are developed with modular sub-components for decision-making, planning, and control…

Multimodal recommendation focuses primarily on effectively exploiting both behavioral and multimodal information for the recommendation task. However, most existing models suffer from the following issues when fusing information from two…

We present a motion planning algorithm for a class of uncertain control-affine nonlinear systems which guarantees runtime safety and goal reachability when using high-dimensional sensor measurements (e.g., RGB-D images) and a learned…

Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, such as structured databases or knowledge graphs, accessed…

Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a…

Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model…

Retrieval-Augmented Generation (RAG) aims to mitigate hallucinations in large language models (LLMs) by grounding responses in retrieved documents. Yet, RAG-based LLMs still hallucinate even when provided with correct and sufficient…

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions. Traditional RGB-T detectors assume balanced training data, where both modalities contribute…

Object hallucination in large vision-language models presents a significant challenge to their safe deployment in real-world applications. Recent works have proposed object-level hallucination scores to estimate the likelihood of object…

Machine Translation (MT) is undergoing a paradigm shift, with systems based on fine-tuned large language models (LLM) becoming increasingly competitive with traditional encoder-decoder models trained specifically for translation tasks.…

Despite the promising progress in multi-modal tasks, current large multi-modal models (LMMs) are prone to hallucinating inconsistent descriptions with respect to the associated image and human instructions. This paper addresses this issue…

Multimodal machine learning with missing modalities is an increasingly relevant challenge arising in various applications such as healthcare. This paper extends the current research into missing modalities to the low-data regime, i.e., a…

Deep reinforcement learning provides a promising approach for vision-based control of real-world robots. However, the generalization of such models depends critically on the quantity and variety of data available for training. This data can…

Recent work has demonstrated state-of-the-art results in large language model (LLM) hallucination detection and mitigation through consistency-based approaches which involve aggregating multiple responses sampled from a single LLM for a…

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…