Related papers: On the Generalization Capacities of MLLMs for Spat…

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM,…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Do we still need to represent objects explicitly in multimodal large language models (MLLMs)? To one extreme, pre-trained encoders convert images into visual tokens, with which objects and spatiotemporal relationships may be implicitly…

Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception…

Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental challenge in Multi-Modal Large Language Models (MLLMs) to…

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However,…

Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human…

In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly…

Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space. In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce…

Spatial cognition is fundamental to real-world multimodal intelligence, allowing models to effectively interact with the physical environment. While multimodal large language models (MLLMs) have made significant strides, existing benchmarks…

Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental monitoring. However, generalist Large Multi-modal Models (LMMs) are typically trained on RGB…

Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

Objectives: The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly enhanced their reasoning capabilities, enabling a wide range of intelligent applications. However, these advancements also raise critical…

Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input…

Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing…