no code implementations • 28 Jan 2024 • Yihao Wang, Ruiqi Song, Ru Zhang, Jianyi Liu, Lingxiao Li
Regarding open-source LLMs, we reconstruct the token generator of LLM to the "stego generator" so that it can control the generation of stego based on the secret.
no code implementations • 3 Nov 2023 • Yihao Wang, Ruiqi Song, Ru Zhang, Jianyi Liu
In this paper, we propose the UP4LS, a novel framework with the User Profile for enhancing LS performance.
no code implementations • CVPR 2023 • Yihao Wang, Zhigang Wang, Bin Zhao, Dong Wang, Mulin Chen, Xuelong Li
In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e. g., security.
1 code implementation • Findings (ACL) 2022 • Rui Cao, Yihao Wang, Yuxin Liang, Ling Gao, Jie Zheng, Jie Ren, Zheng Wang
We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples.
no code implementations • 20 Oct 2021 • Yihao Wang, Ling Gao, Jie Ren, Rui Cao, Hai Wang, Jie Zheng, Quanli Gao
In detail, we train a DNN model (termed as pre-model) to predict which object detection model to use for the coming task and offloads to which edge servers by physical characteristics of the image task (e. g., brightness, saturation).
no code implementations • 7 Oct 2021 • Yihao Wang
Based on the snapshot ensemble, we present a new method that is easier to implement: unlike original snapshot ensemble that seeks for local minima, our snapshot ensemble focuses on the last few iterations of a training and stores the sets of parameters from them.
1 code implementation • 15 Mar 2021 • Xuequan Lu, Yihao Wang, Sheldon Fung, Xue Qing
In this paper, we identify two main bottlenecks: (1) the lack of a publicly available imaging dataset for diverse species of nematodes (especially the species only found in natural environment) which requires considerable human resources in field work and experts in taxonomy, and (2) the lack of a standard benchmark of state-of-the-art deep learning techniques on this dataset which demands the discipline background in computer science.
no code implementations • 23 Dec 2019 • Yihao Wang, Katsushi Hashimoto, Toru Tomimatsu, Yoshiro Hirayama
While the disorder-induced quantum Hall (QH) effect has been studied previously, the effect ofdisorder potential on microscopic features of the integer QH effect remains unclear, particularly forthe incompressible (IC) strip.
Mesoscale and Nanoscale Physics