no code implementations • 6 Dec 2023 • Haichao Sha, Ruixuan Liu, Yixuan Liu, Hong Chen
We prove that pre-projection enhances the convergence of DP-SGD by reducing the dependence of clipping error and bias to a fraction of the top gradient eigenspace, and in theory, limits cross-client variance to improve the convergence under heterogeneous federation.
2 code implementations • 25 Aug 2023 • Tong Xie, Yuwei Wan, Wei Huang, Zhenyu Yin, Yixuan Liu, Shaozhou Wang, Qingyuan Linghu, Chunyu Kit, Clara Grazian, Wenjie Zhang, Imran Razzak, Bram Hoex
To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science.
no code implementations • 11 Apr 2023 • Yixuan Liu, Suyun Zhao, Li Xiong, YuHan Liu, Hong Chen
In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model.
no code implementations • 5 Apr 2023 • Tong Xie, Yuwei Wan, Wei Huang, Yufei Zhou, Yixuan Liu, Qingyuan Linghu, Shaozhou Wang, Chunyu Kit, Clara Grazian, Wenjie Zhang, Bram Hoex
The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches.
no code implementations • 9 Mar 2023 • Jie Liu, Yixuan Liu, Xue Han, Chao Deng, Junlan Feng
Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.
1 code implementation • ACL 2022 • Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang, Yixuan Liu
However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated.
no code implementations • 1 Dec 2021 • Chengxiu Ling, Jiayi Li, Yixuan Liu, Zhiyan Cai
Catastrophic losses caused by natural disasters receive a growing concern about the severe rise in magnitude and frequency.
1 code implementation • 30 Nov 2021 • Yixuan Liu, Chrysafis Vogiatzis, Ruriko Yoshida, Erich Morman
Uncrewed autonomous vehicles (UAVs) have made significant contributions to reconnaissance and surveillance missions in past US military campaigns.
no code implementations • 21 Feb 2021 • Yixuan Liu, Hu Wang, Xiaowei Wang, Xiaoyue Sun, Liuyue Jiang, Minhui Xue
Therefore, a purify-trained classifier is designed to obtain the distribution and generate the calibrated rewards.
no code implementations • ECCV 2020 • Zhongdao Wang, Jingwei Zhang, Liang Zheng, Yixuan Liu, Yifan Sun, Ya-Li Li, Shengjin Wang
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
12 code implementations • ECCV 2020 • Zhongdao Wang, Liang Zheng, Yixuan Liu, Ya-Li Li, Shengjin Wang
In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
Ranked #4 on Multi-Object Tracking on HiEve
no code implementations • 4 Aug 2019 • Yixuan Liu, Yuwang Wang, Shengjin Wang
To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.