相关论文: From Correspondence to Actions: Human-Like Multi-I…

Vision-language models (VLMs) increasingly combine visual and textual information to perform complex tasks. However, conflicts between their internal knowledge and external visual input can lead to hallucinations and unreliable predictions.…

While multimodal large language models (MLLMs) are increasingly applied in human-centred AI systems, their ability to understand complex social interactions remains uncertain. We present an exploratory study on aligning MLLMs with…

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…

Multi-Object Tracking (MOT) is evolving from geometric localization to Semantic MOT (SMOT) to answer complex relational queries, yet progress is hindered by semantic data scarcity and a structural disconnect between tracking architectures…

Multimodal large language models (MLLMs) demonstrate strong perception and reasoning performance on existing remote sensing (RS) benchmarks. However, most prior benchmarks rely on low-resolution imagery, and some high-resolution benchmarks…

Establishing semantic correspondence across images when the objects in the images have undergone complex deformations remains a challenging task in the field of computer vision. In this paper, we propose a hierarchical method to tackle this…

Cross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), especially in achieving precise point-level correspondence,…

Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning…

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific…

Large Language Models (LLMs) and Large Multi-modality Models (LMMs) have demonstrated remarkable decision masking capabilities on a variety of tasks. However, they inherently operate planning within the language space, lacking the vision…

Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic…

Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them. Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual…

Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…

Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…

Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language tasks. In robotics, similar embodied CoT strategies,…

Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D…

Large multimodal models (LMMs) show strong visual-linguistic reasoning but their capacity for spatial decision-making and action remains unclear. In this work, we investigate whether LMMs can achieve embodied spatial action like human…