8 papers
ForeFly: A Dual-Horizon World Action Model for Aerial Vision-Language Navigation
Kunhui Wang, Xintong Zhang, Junyu Gao +1
Aerial Vision-Language Navigation (AVLN) requires UAVs to maintain reliable instruction following over long trajectories in complex 3D environments. However, existing AVLN approach…
SC-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
Xuan Yao, Yuze Zhu, Junyu Gao +2
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observability. However, most existing met…
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
Xuan Yao, Junyu Gao, Changsheng Xu
Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instr…
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Mengyuan Chen, Junyu Gao, Changsheng Xu
A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-train…
Revisiting Essential and Nonessential Settings of Evidential Deep Learning
Mengyuan Chen, Junyu Gao, Changsheng Xu
Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant atten…
A Comprehensive Survey on Evidential Deep Learning and Its Applications
Junyu Gao, Mengyuan Chen, Liangyu Xiang +1
Reliable uncertainty estimation has become a crucial requirement for the industrial deployment of deep learning algorithms, particularly in high-risk applications such as autonomou…
Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation
Junyu Gao, Xuan Yao, Changsheng Xu
The ability to accurately comprehend natural language instructions and navigate to the target location is essential for an embodied agent. Such agents are typically required to exe…
Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation
Junyu Gao, Xinhong Ma, Changsheng Xu
Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting…