Papers

2023

• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [Arxiv]
  Fuzhao Xue, Yao Fu, Wangchunshu Zhou, Zangwei Zheng, Yang You arXiv preprint arXiv:2305.13230

• Adaptive Computation with Elastic Input Sequence [Arxiv] [Code]
  Fuzhao Xue, Valerii Likhosherstov, Anurag Arnab, Neil Houlsby, Mostafa Dehghani, Yang You Accepted at International Conference on Machine Learning (ICML) 2023 (Acceptence rate: 27.9%)

• A Study on Transformer Configuration and Training Objective [Arxiv] [Code]
  Fuzhao Xue, Jianghai Chen, Aixin Sun, Xiaozhe Ren, Zangwei Zheng, Xiaoxin He, Yongming Chen, Xin Jiang, Yang You Accepted at International Conference on Machine Learning (ICML) 2023 (Acceptence rate: 27.9%)

• Sequence Parallelism: Long Sequence Training from System Perspective [Arxiv] [Code] [Video]
  Shenggui Li *, Fuzhao Xue * , Yongbin Li, Yang You Accepted at Association for Computational Linguistics (ACL) 2023 (* indicates equal contribution)

• Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline [Arxiv] [Code] [Blog]
  Zangwei Zheng, Xiaozhe Ren, Fuzhao Xue, Yang Luo, Xin Jiang, Yang You arXiv preprint arXiv:2305.13144

• CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU [Arxiv] [Code]
  Zangwei Zheng, Pengtai Xu, Xuan Zou, Da Tang, Zhen Li, Chenguang Xi, Peng Wu, Leqi Zou, Yijie Zhu, Ming Chen, Xiangzhuo Ding, Fuzhao Xue, Ziheng Qing, Youlong Cheng, Yang You *Accepted at Association for the Advancement of Artificial Intelligence (AAAI) 2023 Distinguished Paper Award (0.13%, 12 of 8777 submissions) *

• Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention [Arxiv] [Code]
  Xiao Liu, Jian Zhang, Heng Zhang, Fuzhao Xue, Yang You Accepted at International Conference on Learning Representations (ICLR Tiny Paper) 2023

2022

• Go Wider Instead of Deeper [Arxiv] [Code]
  Fuzhao Xue, Ziji Shi, Yuxuan Lou, Yong Liu, Yang You Published at Association for the Advancement of Artificial Intelligence (AAAI) 2022 (Acceptence rate: 15.0%)

• An Embarrassingly Simple Model for Dialogue Relation Extraction [Arxiv] [Code] [Slides] [Poster]
  Fuzhao Xue, Aixin Sun, Hao Zhang, Eng-Siong Chng Published at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022

• One Student Knows All Experts Know: From Sparse to Dense [Arxiv]
  Fuzhao Xue, Xiaoxin He, Xiaozhe Ren, Yuxuan Lou, Yang You arXiv preprint arXiv:2201.10890

• Recent Advances in Deep Learning-based Dialogue Systems [Arxiv]
  Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Vinay Adiga, Erik Cambria Published at Artificial Intelligence Review

• Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization [Arxiv]
  Andrew Koh, Fuzhao Xue, Eng Siong Chng Published at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022

• Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation [Arxiv] [Code]
  Wangbo Zhao, Kai Wang, Xiangxiang Chu, Fuzhao Xue, Xinchao Wang, and Yang You Published at IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Acceptence rate: 25.3%)

2021

• GDPNet: Refining Latent Multi-View Graph for Relation Extraction [Arxiv] [Code] [Video] [Slides] [Poster]
  Fuzhao Xue, Aixin Sun, Hao Zhang, Eng-Siong Chng Published at Association for the Advancement of Artificial Intelligence (AAAI) 2021 (Acceptence rate: 21.4%)

• Large-Scale Deep Learning Optimizations: A Comprehensive Survey [Arxiv]
  Xiaoxin He, Fuzhao Xue, Xiaozhe Ren, Yang You

• Cross-token Modeling with Conditional Computation [Arxiv]
  Yuxuan Lou, Fuzhao Xue, Zangwei Zheng, Yang You

• RACP: A network with Attention Corrected Prototype for Few-shot Speaker Recognition using Indefinite Distance Metric
  Xingmei Wang, Jiaxiang Meng, Bin Wen, Fuzhao Xue Published at Neurocomputing

2020

• Deep Graph Random Process for Relational-Thinking-Based Speech Recognition [Arxiv]
  Hengguan Huang, Fuzhao Xue, Hao Wang, Ye Wang Published at International Conference on Machine Learning (ICML) 2020 (Acceptence rate: 21.5%)

• A network model of speaker identification with new feature extraction methods and asymmetric BLSTM
  Xingmei Wang, Fuzhao Xue, Wei Wang, Anhua Liu Published at Neurocomputing

2019

• An Underwater Acoustic Target Recognition: A Combination of Multi-dimensional Fusion Features and Modified Deep Neural Network
  Xingmei Wang, Anhua Liu, Yu Zhang, Fuzhao Xue Published at Remote Sensing