Related papers: Multiplication in Multimodal LLMs: Computation wit…

With enhanced capabilities and widespread applications, Multimodal Large Language Models (MLLMs) are increasingly required to process and reason over multiple images simultaneously. However, existing MLLM benchmarks focus either on…

Alignment with high-resource standard languages is often assumed to aid the modeling of related low-resource varieties. We challenge this assumption by demonstrating that excessive representational entanglement with a dominant variety, such…

Numeral systems and units of measurement are two conjoined topics in activities of human beings and have mutual effects with the languages expressing them. Currently, the evaluation of Large Language Models (LLMs) often involves…

Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess…

Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. MLLMs have shown promising capability in aligning visual and textual modalities, allowing them to process image-text…

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and…

Multimodal large language models (MLLMs) have achieved strong performance on perception-oriented tasks, yet their ability to perform mathematical spatial reasoning, defined as the capacity to parse and manipulate two- and three-dimensional…

Multimodal large language models (MLLMs) have advanced rapidly, yet heterogeneity in architecture, alignment strategies, and efficiency means that no single model is uniformly superior across tasks. In practical deployments, workloads span…

Textual descriptions for multimodal inputs entail recurrent refinement of queries to produce relevant output images. Despite efforts to address challenges such as scaling model size and data volume, the cost associated with pre-training and…

Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal…

Recent research has increasingly focused on multimodal mathematical reasoning, particularly emphasizing the creation of relevant datasets and benchmarks. Despite this, the role of visual information in reasoning has been underexplored. Our…

Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual semantic arithmetic, inferring relationships from images,…

This paper investigates the inverse capabilities and broader utility of multimodal latent spaces within task-specific AI (Artificial Intelligence) models. While these models excel at their designed forward tasks (e.g., text-to-image…

Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image, a question, and several options. However, many benchmarks…

Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input…

State-of-the-art vision-and-language models consist of many parameters and learn from enormous datasets, surpassing the amounts of linguistic data that children are exposed to as they acquire a language. This paper presents our approach to…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant potential in recommendation systems. However, the effective application of MLLMs to multimodal sequential recommendation remains unexplored: A)…

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…

Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting superior performance compared to the conventional ID-based recommender systems. However,…