相关论文: Zoom Consistency: A Free Confidence Signal in Mult…

Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…

GUI grounding, which localizes interface elements from screenshots given natural language queries, remains challenging for small icons and dense layouts. Test-time zoom-in methods improve localization by cropping and re-running inference at…

We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standard benchmarks measure only final-answer accuracy, which obscures how models use visual…

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has focused on improving subcomponents of estimation pipelines, to…

Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equivalent descriptions yield consistent outputs. We examine this assumption using a controlled…

Terrain traversability estimation is crucial for autonomous robots, especially in unstructured environments where visual cues and reasoning play a key role. While vision-language models (VLMs) offer potential for zero-shot estimation, the…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop…

In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition, where physically meaningful quantities such as distances and motion statistics must be measured in meters.…

ECG digitization could unlock billions of archived clinical records, yet existing methods collapse on real-world images despite strong benchmark numbers. We introduce \textbf{VLM-in-the-Loop}, a plug-in quality assurance module that wraps…

Diffusion models accomplish remarkable success in data generation tasks across various domains. However, the iterative sampling process is computationally expensive. Consistency models are proposed to learn consistency functions to map from…

Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and…

When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion. However, there is no work to explore the possibility of the reverse - going from completion to task specification. In…

Autonomous inspection of underground infrastructure, such as sewer and culvert systems, is critical to public safety and urban sustainability. Although robotic platforms equipped with visual sensors can efficiently detect structural…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we explore their potential for object grounding in remote sensing imagery. We propose a…

Grounding is a fundamental capability for building graphical user interface (GUI) agents. Although existing approaches rely on large-scale bounding box supervision, they still face various challenges, such as cross-platform generalization,…

Online augmentation of an oblique aerial image sequence with structural information is an essential aspect in the process of 3D scene interpretation and analysis. One key aspect in this is the efficient dense image matching and depth…