collaborators

7 papers

cs.RO2026

From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation

Xiangyu Shi, Ruoxi Yang, Wei Tao +3

Vision-and-Language Navigation (VLN) agents may satisfy conventional success criteria while still failing to establish reliable object-level grounding, because current evaluation p…

cs.RO2026

SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation

Jiwen Zhang, Xiangyu Shi, Siyuan Wang +3

Vision-and-Language Navigation (VLN) has recently benefited from Multimodal Large Language Models (MLLMs), enabling zero-shot navigation. While recent exploration-based zero-shot m…

cs.RO2026

ROI-Driven Foveated Attention for Unified Egocentric Representations in Vision-Language-Action Systems

Xinhai Sun, Xiang Shi, Menglin Zou +1

The development of embodied AI systems is increasingly constrained by the availability and structure of physical interaction data. Despite recent advances in vision-language-action…

cs.CV2026

SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation

Jiwen Zhang, Zejun Li, Siyuan Wang +3

Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, r…

cs.RO2025

Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation

Xiangyu Shi, Zerui Li, Yanyuan Qiao +1

Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. Howev…

cs.RO2025

Embodied Domain Adaptation for Object Detection

Xiangyu Shi, Yanyuan Qiao, Lingqiao Liu +1

Mobile robots rely on object detectors for perception and object localization in indoor environments. However, standard closed-set methods struggle to handle the diverse objects an…