相关论文: Tactile Hallucinations on Artificial Skin Induced …

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Brain-computer interface allows people who have lost their motor skills to control robot limbs based on electroencephalography. Most BCIs are guided only by visual feedback and do not have somatosensory feedback, which is an important…

This theoretical work examines 'hallucinations' in both human cognition and large language models, comparing how each system can produce perceptions or outputs that deviate from reality. Drawing on neuroscience and machine learning…

Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit "hallucinations," samples that could never occur in the training data. But where do such hallucinations come from? In this paper,…

Understanding sensory-induced cortical patterns in the primary visual cortex V1 is an important challenge both for physiological motivations and for improving our understanding of human perception and visual organisation. In this work, we…

AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, such hallucinations are not equally problematic: some hallucination contents could be…

In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail…

Developing artificial tactile sensing capabilities that rival human touch is a long-term goal in robotics and prosthetics. Gradually more elaborate biomimetic tactile sensors are being developed and applied to grasping and manipulation…

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…

Touch is the first sense among human senses. Not only that, but it is also one of the most important senses that are indispensable. However, compared to sight and hearing, it is often neglected. In particular, since humans use the tactile…

Recently simulation methods have been developed for optical tactile sensors to enable the Sim2Real learning, i.e., firstly training models in simulation before deploying them on the real robot. However, some artefacts in the real objects…

We investigate the transduction of tactile information during active exploration of finely textured surfaces using a novel tactile sensor mimicking the human fingertip. The sensor has been designed by integrating a linear array of 10…

Diffusion models, despite their impressive demos, often produce hallucinatory samples with structural inconsistencies that lie outside of the support of the true data distribution. Such hallucinations can be attributed to excessive…

Localization of a macroscopic number of eigenstates on a real-space boundary, known as the non-Hermitian skin effect, is one of the striking topological features emerging from non-Hermiticity. Realizing this effect typically requires…

Most current works in Sim2Real learning for robotic manipulation tasks leverage camera vision that may be significantly occluded by robot hands during the manipulation. Tactile sensing offers complementary information to vision and can…

Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the image. This weakness of MLLMs is currently studied using static benchmarks with fixed…

At the core of bodily self-consciousness is the perception of the ownership of one's body. Recent efforts to gain a deeper understanding of the mechanisms behind the brain's encoding of the self-body have led to various attempts to develop…

Playing back vibrotactile signals through actuators is commonly used to simulate tactile feelings of virtual textured surfaces. However, there is often a small mismatch between the simulated tactile feelings and intended tactile feelings by…

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of…

Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate…