相关论文: GRAID: Enhancing Spatial Reasoning of VLMs Through…

Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as…

Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet their performance in open aerial environments remains underexplored. In this work, we present Open3D-VQA, a novel benchmark for evaluating MLLMs'…

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…

Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already…

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This…

Vision-language models (VLMs) have achieved remarkable success in scene understanding and perception tasks, enabling robots to plan and execute actions adaptively in dynamic environments. However, most multimodal large language models lack…

We present GR3D, a spatial vision language model equipped with three complementary grounding capabilities--explicit 2D grounding, implicit 2D grounding, and monocular 3D grounding--within a single framework. GR3D introduces an implicit…

Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on explicit 3D inputs or specialized model architectures, we ask:…

Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluating whether language models can produce spatially correct animated outputs remains an…

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…

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single…

Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs). Prior work largely relied on synthetic or LLM-generated environments with limited task designs…

Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling…

Recent advances in Multi-modal Large Language Models (MLLMs) target 3D spatial intelligence, yet the progress has been largely driven by post-training on curated benchmarks, leaving the inference-time approach relatively underexplored. In…

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks but still struggle with fine-grained visual differences, leading to hallucinations or missed semantic shifts. We attribute this to…

We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously…

Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) techniques have exhibited remarkable performance across a wide range of domains. However, existing RAG approaches primarily operate on unstructured data and…

The Large Visual Language Models (LVLMs) enhances user interaction and enriches user experience by integrating visual modality on the basis of the Large Language Models (LLMs). It has demonstrated their powerful information processing and…

What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual…