Related papers: Simulating Validity: Modal Decoupling in MLLM Gene…
Cultural values are expressed not only through language but also through visual scenes and everyday social practices. Yet existing evaluations of cultural values in language models are almost entirely text-only, making it unclear whether…
Visual Grounding (VG) methods in Visual Question Answering (VQA) attempt to improve VQA performance by strengthening a model's reliance on question-relevant visual information. The presence of such relevant information in the visual input…
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…
Large language models (LLMs) have demonstrated significant capabilities in mathematical reasoning, particularly with text-based mathematical problems. However, current multi-modal large language models (MLLMs), especially those specialized…
Grounding has been argued to be a crucial component towards the development of more complete and truly semantically competent artificial intelligence systems. Literature has divided into two camps: While some argue that grounding allows for…
Service robots should be able to interact naturally with non-expert human users, not only to help them in various tasks but also to receive guidance in order to resolve ambiguities that might be present in the instruction. We consider the…
Multi-view learning methods often focus on improving decision accuracy, while neglecting the decision uncertainty, limiting their suitability for safety-critical applications. To mitigate this, researchers propose trusted multi-view…
Visual grounding, a crucial vision-language task involving the understanding of the visual context based on the query expression, necessitates the model to capture the interactions between objects, as well as various spatial and attribute…
Multimodal Large Language Models (MLLMs) demonstrate robust zero-shot capabilities across diverse vision-language tasks after training on mega-scale datasets. However, dense prediction tasks, such as semantic segmentation and keypoint…
Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input. We investigate the root causes…
Recent advancements in large language models (LLMs) have revitalized philosophical debates surrounding artificial intelligence. Two of the most fundamental challenges - namely, the Frame Problem and the Symbol Grounding Problem - have…
Multimodal Large Language Models (MLLMs) exhibit impressive capabilities across a variety of tasks, especially when equipped with carefully designed visual prompts. However, existing studies primarily focus on logical reasoning and visual…
Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…
Reliable evaluation is essential in machine learning research, yet methodological flaws-particularly data leakage-continue to undermine the validity of reported results. In this work, we investigate whether large language models (LLMs) can…
Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread across multiple regions, as in documents and compositional queries. We address this by framing…
In recent years, multimodal large language models (MLLMs) have achieved significant breakthroughs, enhancing understanding across text and vision. However, current MLLMs still face challenges in effectively integrating knowledge across…
Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack the ground locations and relations for visual entities.…
Misleading visualizations, which manipulate chart representations to support specific claims, can distort perception and lead to incorrect conclusions. Despite decades of research, they remain a widespread issue, posing risks to public…
Large language models (LLMs) struggle with formal domains that require rigorous logical deduction and symbolic reasoning, such as mathematical proof generation. We propose a neuro-symbolic approach that combines LLMs' generative strengths…
Automated grading systems have enabled scalable assessment for many response types, but handwritten mathematics remains a barrier due to the complexity of multi-step solutions. Vision-capable large language models (LLMs) offer new…