相关论文: PostAlign: Multimodal Grounding as a Corrective Le…

Visual grounding focuses on detecting objects from images based on language expressions. Recent Large Vision-Language Models (LVLMs) have significantly advanced visual grounding performance by training large models with large-scale…

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g.,…

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance…

Establishing a clear link between model predictions and the visual evidence that supports them is critical for transparency and reliability in multimodal reasoning, yet current multimodal large language model (MLLM) evaluations do not…

Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance…

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…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate…

Although Large Vision-Language Models (LVLMs) have made substantial progress, hallucination, where generated text is not grounded in the visual input, remains a challenge. As LVLMs become stronger, previously reported hallucination…

Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from…

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…

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual…

In this work, we identify an inherent bias in prevailing LVLM architectures toward the language modality, largely resulting from the common practice of simply appending visual embeddings to the input text sequence. To address this, we…

Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically,…

Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do…

Embodied agents operating in smart homes must understand human behavior through diverse sensory inputs and communicate via natural language. While Vision-Language Models (VLMs) have enabled impressive language-grounded perception, their…

This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the…

The rapidly developing Large Vision Language Models (LVLMs) have shown notable capabilities on a range of multi-modal tasks, but still face the hallucination phenomena where the generated texts do not align with the given contexts,…

Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accurate visual understanding. To address this issue, we propose…

Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce…