6 papers
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…
Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition
Wen Guo, Pengfei Zhao, Zongmeng Wang +2
Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in…
HulluEdit: Single-Pass Evidence-Consistent Subspace Editing for Mitigating Hallucinations in Large Vision-Language Models
Yangguang Lin, Quan Fang, Yufei Li +3
Object hallucination in Large Vision-Language Models (LVLMs) significantly hinders their reliable deployment. Existing methods struggle to balance efficiency and accuracy: they oft…
Cross-Modal Dual-Causal Learning for Long-Term Action Recognition
Xu Shaowu, Jia Xibin, Gao Junyu +3
Long-term action recognition (LTAR) is challenging due to extended temporal spans with complex atomic action correlations and visual confounders. Although vision-language models (V…
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…