6 accepted papers
Zero-shot object navigation (ZSON) in unseen environments poses a significant challenge due to the absence of object-specific priors and the need for efficient exploration. Existing approaches often struggle with ineffective search strategies and repeated visits to irrelevant areas. In this paper, w
Adversarial vulnerabilities in vision-language models pose a critical challenge to the reliability of large language systems, where typographic manipulations and adversarial perturbations can effectively bypass language model defenses. We introduce Attack as Defense (AsD), the first approach to proa
Typographic attacks are often attributed to the ability of multimodal pre-trained models to fuse textual semantics into visual representations, yet the mechanisms and locus of such interference remain unclear. We examine whether such models genuinely encode textual semantics or primarily rely on tex…
The intrinsic dimension (ID) represents the minimum dimension needed to describe data on a lower-dimensional manifold within high-dimensional spaces. Network pruning aims to reduce the complexity of high-dimensional networks while minimizing performance trade-offs. This symmetry motivates the explor…
The perception-aware motion planning method based on the localization uncertainty has the potential to improve the localization accuracy for robot navigation. How-ever, most of the existing perception-aware methods pre-build a global feature map and can not generate the perception- aware trajectory…
Vision-to-language tasks require a unified semantic understanding of visual content. However, the information contained in image/video is essentially ambiguous on two perspectives manifested on the diverse understanding among different persons and the various understanding grains even for the same p…