相关论文: Make VLM Recognize Visual Hallucination on Cartoon…

Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image…

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing…

Recent Large Vision-Language Models (LVLMs) have shown promising reasoning capabilities on text-rich images from charts, tables, and documents. However, the abundant text within such images may increase the model's sensitivity to language.…

Recent generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts. Nevertheless, a significant challenge remains in applying these models for the more…

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the generation of factually incorrect or inconsistent responses.…

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in tasks such as abnormality detection and report generation for anatomical modalities, their capability in functional imaging remains largely…

Hallucinations pose a significant challenge to the reliability of large vision-language models, making their detection essential for ensuring accuracy in critical applications. Current detection methods often rely on computationally…

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, leading to object hallucination. To tackle this, recent works…

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

Situational awareness applications rely heavily on real-time processing of visual and textual data to provide actionable insights. Vision language models (VLMs) have become essential tools for interpreting complex environments by connecting…

The recent developments in deep learning led to the integration of natural language processing (NLP) with computer vision, resulting in powerful integrated Vision and Language Models (VLMs). Despite their remarkable capabilities, these…

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual…

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in…

Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

As data requirements continue to grow, efficient learning increasingly depends on the curation and distillation of high-value data rather than brute-force scaling of model sizes. In the case of a hyperspectral image (HSI), the challenge is…