Related papers: Injecting Hallucinations in Autonomous Vehicles: A…

Large Vision-Language Models (LVLMs) have achieved impressive progress in multimodal reasoning, yet they remain prone to object hallucinations, generating descriptions of objects that are not present in the input image. Recent approaches…

Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically operate after text generation, making intervention both costly…

Vision language models (VLMs) perceive the world through a combination of a visual encoder and a large language model (LLM). The visual encoder, pre-trained on large-scale vision-text datasets, provides zero-shot generalization to visual…

Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between…

Recently, 3D-LLMs, which combine point-cloud encoders with large models, have been proposed to tackle complex tasks in embodied intelligence and scene understanding. In addition to showing promising results on 3D tasks, we found that they…

Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major challenge compromising their reliability is object hallucination…

Virtual scenario-based testing methods to validate autonomous driving systems are predominantly centred around collision avoidance, and lack a comprehensive approach to evaluate optimal driving behaviour holistically. Furthermore, current…

Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming from both environmental and system-level factors. These…

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

Inter-vehicle communication for autonomous vehicles (AVs) stands to provide significant benefits in terms of perception robustness. We propose a novel approach for AVs to communicate perceptual observations, tempered by trust modelling of…

While automated driving technology has achieved a tremendous progress, the scalable and rigorous testing and verification of safe automated and autonomous driving vehicles remain challenging. This paper proposes a learning-based…

High-speed cruising scenarios with mixed traffic greatly challenge the road safety of autonomous vehicles (AVs). Unlike existing works that only look at fundamental modules in isolation, this work enhances AV safety in mixed-traffic…

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent…

Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information. In this paper, we systematically study the object hallucination problem from three…

As students increasingly rely on large language models, hallucinations pose a growing threat to learning. To mitigate this, AI literacy must expand beyond prompt engineering to address how students should detect and respond to LLM…

High-level Autonomous Driving Systems (ADSs), such as Google Waymo and Baidu Apollo, typically rely on multi-sensor fusion (MSF) based approaches to perceive their surroundings. This strategy increases perception robustness by combining the…

Connected Autonomous Vehicles have great potential to improve automobile safety and traffic flow, especially in cooperative applications where perception data is shared between vehicles. However, this cooperation must be secured from…

Large language models (LLMs) are growingly extended to process multimodal data such as text and video simultaneously. Their remarkable performance in understanding what is shown in images is surpassing specialized neural networks (NNs) such…

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…

Hallucinations are outputs by Large Language Models (LLMs) that are factually incorrect yet appear plausible [1]. This paper investigates how such hallucinations influence users' trust in LLMs and users' interaction with LLMs. To explore…