Related papers: Does Visual Grounding Enhance the Understanding of…

What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input comes from a…

Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks. However, their visual understanding behaviors remain underexplored. A fundamental question arises: to what extent do…

Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models truly understand the content they process. Crucially, can VLMs detect when a reasoning process…

Large vision-language models (VLMs) achieve strong performance on multimodal tasks but often suffer from hallucination and poor grounding in knowledge-intensive reasoning. We propose SmoGVLM, a small, graph-enhanced VLM that integrates…

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model…

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs…

The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However,…

Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale…

Does seeing always mean knowing? Large Vision-Language Models (LVLMs) integrate separately pre-trained vision and language components, often using CLIP-ViT as vision backbone. However, these models frequently encounter a core issue of…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…

Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the…

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical…

Multimodal Large Language Models (MLLMs) are gaining increasing popularity in both academia and industry due to their remarkable performance in various applications such as visual question answering, visual perception, understanding, and…

While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting. In this work, we investigate this extrapolation bottleneck by deconstructing…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Multimodal large language models (MLLMs) perform strongly on natural images, yet their ability to understand discrete visual symbols remains unclear. We present a multi-domain benchmark spanning language, culture, mathematics, physics and…

Occlusion perception, a critical foundation for human-level spatial understanding, embodies the challenge of integrating visual recognition and reasoning. Though multimodal large language models (MLLMs) have demonstrated remarkable…

Vision language models (VLMs) are AI systems paired with both language and vision encoders to process multimodal input. They are capable of performing complex semantic tasks such as automatic captioning, but it remains an open question…

Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing…