Related papers: ORIGAMISPACE: Benchmarking Multimodal LLMs in Mult…

The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large language models (LLMs) with human-like reasoning capabilities…

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be…

A key frontier for Multimodal Large Language Models (MLLMs) is the ability to perform deep mathematical and spatial reasoning directly from images, moving beyond their established success in semantic description. Mathematical surface plots…

Under pure textual modality, Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning tasks by decomposing them into simpler sub-problems. However, Multimodal Large Language Models (MLLMs) still struggle with…

Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…

While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…

Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning capabilities.…

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM that integrates…

While logical reasoning evaluation of Large Language Models (LLMs) has attracted significant attention, existing benchmarks predominantly rely on multiple-choice formats that are vulnerable to random guessing, leading to overestimated…

Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning,…

The advent of Multimodal Large Language Models, leveraging the power of Large Language Models, has recently demonstrated superior multimodal understanding and reasoning abilities, heralding a new era for artificial general intelligence.…

Spatial perception and reasoning are core components of human cognition, encompassing object recognition, spatial relational understanding, and dynamic reasoning. Despite progress in computer vision, existing benchmarks reveal significant…

Large Vision-Language Models (LVLMs) excel in multimodal reasoning and have shown impressive performance on various multimodal benchmarks. However, most of these benchmarks evaluate models primarily through multiple-choice or short-answer…

Recent large language models (LLMs) have advanced table understanding capabilities but rely on converting tables into text sequences. While multimodal large language models (MLLMs) enable direct visual processing, they face limitations in…

Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of…

Embodied intelligence, a grand challenge in artificial intelligence, is fundamentally constrained by the limited spatial understanding and reasoning capabilities of current models. Prevailing efforts to address this through enhancing…

AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains a critical bottleneck -- particularly in early-grade maths, which relies heavily on…

Reasoning about spatial relationships between objects is essential for many real-world robotic tasks, such as fetch-and-delivery, object rearrangement, and object search. The ability to detect and disambiguate different objects and identify…

Reasoning is central to a wide range of intellectual activities, and while the capabilities of large language models (LLMs) continue to advance, their performance in reasoning tasks remains limited. The processes and mechanisms underlying…

Robotic path planning problems are often NP-hard, and practical solutions typically rely on approximation algorithms with provable performance guarantees for general cases. While designing such algorithms is challenging, formally proving…