Related papers: World2Mind: Cognition Toolkit for Allocentric Spat…

Standard Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs) with reasoning capabilities, yet its reliance on linear natural language is inherently insufficient for effective world modeling in embodied tasks. While text…

A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains…

Latent World Models enhance scene representation through temporal self-supervised learning, presenting a perception annotation-free paradigm for end-to-end autonomous driving. However, the reconstruction-oriented representation learning…

Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems from a dual-bottleneck: input-stage conflict between…

Multi-modal large language models (MLLMs) have shown incredible capabilities in a variety of 2D vision and language tasks. We extend MLLMs' perceptual capabilities to ground and reason about images in 3-dimensional space. To that end, we…

Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack…

While previous multimodal slow-thinking methods have demonstrated remarkable success in single-image understanding scenarios, their effectiveness becomes fundamentally constrained when extended to more complex multi-image comprehension…

Multi-modal reasoning requires the seamless integration of visual and linguistic cues, yet existing Chain-of-Thought methods suffer from two critical limitations in cross-modal scenarios: (1) over-reliance on single coarse-grained image…

Geospatial data offers immense potential for understanding our planet. However, the sheer volume and diversity of this data along with its varied resolutions, timescales, and sparsity pose significant challenges for thorough analysis and…

Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the…

Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their performance varies significantly between languages due to the…

Despite strong performance on vision-language tasks, Multimodal Large Language Models (MLLMs) struggle with mathematical problem-solving, with both open-source and state-of-the-art models falling short of human performance on visual-math…

Existing reasoning segmentation approaches typically fine-tune multimodal large language models (MLLMs) using image-text pairs and corresponding mask labels. However, they exhibit limited generalization to out-of-distribution scenarios…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Humans draw to facilitate reasoning: we draw auxiliary lines when solving geometry problems; we mark and circle when reasoning on maps; we use sketches to amplify our ideas and relieve our limited-capacity working memory. However, such…

While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visual thinking to…

Solving topological grid puzzles requires reasoning over global spatial invariants such as connectivity, loop closure, and region symmetry and remains challenging for even the most powerful large language models (LLMs). To study these…

Large language models (LLMs) and vision language models (VLMs), such as DeepSeek R1,OpenAI o3, and Gemini 2.5 Pro, have demonstrated remarkable reasoning capabilities across logical inference, problem solving, and decision making. However,…

Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of…

Current Large Multimodal Models (LMMs) struggle with high-resolution visual inputs during the reasoning process, as the number of image tokens increases quadratically with resolution, introducing substantial redundancy and irrelevant…