no code implementations • ECCV 2020 • Zhuoning Yuan, Zhishuai Guo, Xiaotian Yu, Xiaoyu Wang, Tianbao Yang
In our experiment, we demonstrate that the proposed frame-work is able to train deep learning models with millions of classes and achieve above 10×speedup compared to existing approaches.
2 code implementations • 19 Feb 2024 • Hanling Yi, Feng Lin, Hongbin Li, Peiyang Ning, Xiaotian Yu, Rong Xiao
This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters.
1 code implementation • 23 Jan 2024 • Feng Lin, Hanling Yi, Hongbin Li, Yifan Yang, Xiaotian Yu, Guangming Lu, Rong Xiao
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency.
no code implementations • CVPR 2023 • Xiaotian Yu, Yang Jiang, Tianqi Shi, Zunlei Feng, Yuexuan Wang, Mingli Song, Li Sun
To address this problem, the proposed GSS alleviates the damage by switching the current gradient direction of each sample to a new direction selected from a gradient direction pool, which contains all-class gradient directions with different probabilities.
1 code implementation • 21 Mar 2022 • Xiaotian Yu, Yifan Yang, Aibo Wang, Ling Xing, Hanling Yi, Guangming Lu, Xiaoyu Wang
Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management.
1 code implementation • 9 Dec 2021 • Zunlei Feng, Jiacong Hu, Sai Wu, Xiaotian Yu, Jie Song, Mingli Song
The aggregate gradient strategy is a versatile module for mainstream CNN classifiers.
no code implementations • 30 Jul 2021 • Xiaotian Yu, Hanling Yi, Yi Yu, Ling Xing, Shiliang Zhang, Xiaoyu Wang
There has been a recent surge of research interest in attacking the problem of social relation inference based on images.
no code implementations • 20 Mar 2019 • Xiaotian Yu
Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e. g., online advertisements.
no code implementations • NeurIPS 2018 • Han Shao, Xiaotian Yu, Irwin King, Michael R. Lyu
In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0, 1]$.