Related papers: Looking Back and Forth: Cross-Image Attention Cali…

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…

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the…

Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of…

While Large Vision-Language Models (LVLMs) achieve strong performance in multimodal tasks, hallucinations continue to hinder their reliability. Among the three categories of hallucinations, which include object, attribute, and relation,…

The troubling rise of hallucination presents perhaps the most significant impediment to the advancement of responsible AI. In recent times, considerable research has focused on detecting and mitigating hallucination in Large Language Models…

Recently, Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multi-modal context comprehension. However, they still suffer from hallucination problems referring to generating inconsistent outputs with the…

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models,…

While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they exhibit persistent hallucination issues, generating outputs misaligned with visual inputs. Recent…

The rapid development of Multi-modality Large Language Models (MLLMs) has significantly influenced various aspects of industry and daily life, showcasing impressive capabilities in visual perception and understanding. However, these models…

Multi-Label Continual Learning (MLCL) builds a class-incremental framework in a sequential multi-label image recognition data stream. The critical challenges of MLCL are the construction of label relationships on past-missing and…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter…

While large vision-language models (LVLMs) have shown impressive capabilities in generating plausible responses correlated with input visual contents, they still suffer from hallucinations, where the generated text inaccurately reflects…

Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent but inconsistent with visual evidence.…

Leveraging large-scale Text-to-Image (TTI) models have become a common technique for generating exemplar or training dataset in the fields of image synthesis, video editing, 3D reconstruction. However, semantic structural visual…

Large vision-language models (LVLMs) exhibit impressive ability to jointly reason over visual and textual inputs. However, they often produce outputs that are linguistically fluent but factually inconsistent with the visual evidence, i.e.,…

Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…

Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs), particularly in real-world applications. Among various mitigation strategies, Retrieval-Augmented Generation (RAG) and reasoning…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…