← Search

Xiuwen Liu

2 accepted papers

2024

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems

IROS 2024

Building on the unprecedented capabilities of large language models for command understanding and zero-shot recognition of multi-modal vision-language transformers, visual language navigation (VLN) has emerged as an effective way to address multiple fundamental challenges toward a natural language i

Cited by 14SourceScholar
2021

Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications

NAACL 2021long

The success of language models based on the Transformer architecture appears to be inconsistent with observed anisotropic properties of representations learned by such models. We resolve this by showing, contrary to previous studies, that the representations do not occupy a narrow cone, but rather d…