no code implementations • 19 Oct 2024 • Ping Huang, Yuxin He, Hao Wang, Jingjing Chen, Qin Luo
Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched.
no code implementations • 17 Sep 2024 • Xiaobao Song, Hao Wang, Liwei Deng, Yuxin He, Wenming Cao, Chi-Sing Leungc
Time position embeddings capture the positional information of time steps, often serving as auxiliary inputs to enhance the predictive capabilities of time series models.
1 code implementation • 29 Apr 2024 • Junhao Cheng, Baiqiao Yin, Kaixin Cai, Minbin Huang, Hanhui Li, Yuxin He, Xi Lu, Yue Li, Yifei Li, Yuhao Cheng, Yiqiang Yan, Xiaodan Liang
To address this issue, we introduce TheaterGen, a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models to provide the capability of multi-turn image generation.
no code implementations • 17 Dec 2023 • Xutong Yue, Xilai Wang, Yuxin He, Zhenkun Zhou
An increasing number of individuals are willing to post states and opinions in social media, which has become a valuable data resource for studying human health.
1 code implementation • 1 Jun 2023 • Yuxin He, Jingyue Hu, Buzhou Tang
Under this framework, we experiment with 3 different training-inference schemes on 4 datasets (ACE05, RAMS, WikiEvents and MLEE) and discover that via training the model to extract all events in parallel, it can better distinguish the semantic boundary of each event and its ability to extract single event gets substantially improved.
no code implementations • ICCV 2023 • Dan Liu, Jin Hou, Shaoli Huang, Jing Liu, Yuxin He, Bochuan Zheng, Jifeng Ning, Jingdong Zhang
To break the deadlock, we present LoTE-Animal, a large-scale endangered animal dataset collected over 12 years, to foster the application of deep learning in rare species conservation.
1 code implementation • Empirical Methods in Natural Language Processing 2022 • Yuxin He, Buzhou Tang
Distinguished from the set-prediction NER framework, our method treats each entity as a sequence and is capable of recognizing discontinuous mentions.
1 code implementation • 16 Apr 2022 • Yinghui Li, Yangning Li, Yuxin He, Tianyu Yu, Ying Shen, Hai-Tao Zheng
In addition, we propose the ProbExpan, a novel probabilistic ESE framework utilizing the entity representation obtained by the aforementioned language model to expand entities.
no code implementations • 28 Jul 2021 • Yuxin He, Lishuai Li, Xinting Zhu, Kwok Leung Tsui
Spatial dependencies, temporal dependencies, inter-station correlations driven by other latent factors, and exogenous factors bring challenges to the short-term forecasts of passenger flow of urban rail transit networks.