相关论文: From dots to faces: Individual differences in visu…

Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly…

Visual illusions in humans arise when interpreting out-of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Recent studies have shown that artificial neural networks (ANNs)…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying…

Neural representations of visual perception are affected by mental imagery and attention. Although attention is known to modulate neural representations, it is unknown how imagery changes neural representations when imagined and perceived…

How do different brains create unique visual experiences from identical sensory input? While neural representations vary across individuals, the fundamental architecture underlying these differences remains poorly understood. Here, we…

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…

Visual illusions may be explained by the likelihood of patches in real-world images, as argued by input-driven paradigms in Neuro-Science. However, neither the data nor the tools existed in the past to extensively support these…

By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust,…

Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a…

The widespread adoption and transformative effects of large language models (LLMs) have sparked concerns regarding their capacity to produce inaccurate and fictitious content, referred to as `hallucinations'. Given the potential risks…

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe…

While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores…

Prominent questions about the role of sensory vs. linguistic input in the way we acquire and use language have been extensively studied in the psycholinguistic literature. However, the relative effect of various factors in a person's…

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…

MLLMs often generate outputs that are inconsistent with the visual content, a challenge known as hallucination. Previous methods focus on determining whether a generated output is hallucinated, without identifying which image region leads…

We study the perception of color illusions by vision-language models. Color illusion, where a person's visual system perceives color differently from actual color, is well-studied in human vision. However, it remains underexplored whether…

The human's visual system detect intensity images. Quite interesting, detector systems have shown the existence of different kind of images. Among them, images obtained by two detectors (detector array or spatially scanning detector)…

Large Language Models have rapidly advanced in their ability to interpret and generate natural language. In enterprise settings, they are frequently augmented with closed-source domain knowledge to deliver more contextually informed…

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…