1 code implementation • 25 Feb 2024 • Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh
DrAttack includes three key components: (a) `Decomposition' of the original prompt into sub-prompts, (b) `Reconstruction' of these sub-prompts implicitly by in-context learning with semantically similar but harmless reassembling demo, and (c) a `Synonym Search' of sub-prompts, aiming to find sub-prompts' synonyms that maintain the original intent while jailbreaking LLMs.
no code implementations • 17 Dec 2023 • Xirui Li, Chao Ma, Xiaokang Yang, Ming-Hsuan Yang
In this work, we propose a novel approach to enhance temporal consistency in generated videos by merging self-attention tokens across frames.
no code implementations • 19 Jun 2023 • Xirui Li, Feng Wang, Naiyan Wang, Chao Ma
To ''forward'' frames, we use vehicle motion models to estimate the future pose of the bounding boxes.
no code implementations • 23 Nov 2021 • Xingkai Zheng, Xirui Li, Ke Xu, Xinghao Jiang, Tanfeng Sun
Most existing gait identification methods extract features from gait videos and identify a probe sample by a query in the gallery.