Zobrazeno 1 - 10
of 179
pro vyhledávání: '"Zhang, James Y."'
Autor:
Wang, Shiyu, Wu, Haixu, Shi, Xiaoming, Hu, Tengge, Luo, Huakun, Ma, Lintao, Zhang, James Y., Zhou, Jun
Time series forecasting is widely used in extensive applications, such as traffic planning and weather forecasting. However, real-world time series usually present intricate temporal variations, making forecasting extremely challenging. Going beyond
Externí odkaz:
http://arxiv.org/abs/2405.14616
Autor:
Jiang, Gangwei, Jiang, Caigao, Xue, Siqiao, Zhang, James Y., Zhou, Jun, Lian, Defu, Wei, Ying
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when fine-tuned
Externí odkaz:
http://arxiv.org/abs/2310.13024
Autor:
Xue, Siqiao, Wang, Yan, Chu, Zhixuan, Shi, Xiaoming, Jiang, Caigao, Hao, Hongyan, Jiang, Gangwei, Feng, Xiaoyun, Zhang, James Y., Zhou, Jun
Neural Temporal Point Processes (TPPs) are the prevalent paradigm for modeling continuous-time event sequences, such as user activities on the web and financial transactions. In real-world applications, event data is typically received in a \emph{str
Externí odkaz:
http://arxiv.org/abs/2310.04993
Autor:
Jin, Ming, Wang, Shiyu, Ma, Lintao, Chu, Zhixuan, Zhang, James Y., Shi, Xiaoming, Chen, Pin-Yu, Liang, Yuxuan, Li, Yuan-Fang, Pan, Shirui, Wen, Qingsong
Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks, models for
Externí odkaz:
http://arxiv.org/abs/2310.01728
Autor:
Wang, Yan, Chu, Zhixuan, Zhou, Tao, Jiang, Caigao, Hao, Hongyan, Zhu, Minjie, Cai, Xindong, Cui, Qing, Li, Longfei, Zhang, James Y, Xue, Siqiao, Zhou, Jun
Asynchronous time series, also known as temporal event sequences, are the basis of many applications throughout different industries. Temporal point processes(TPPs) are the standard method for modeling such data. Existing TPP models have focused on p
Externí odkaz:
http://arxiv.org/abs/2309.02868
Autor:
Chu, Zhixuan, Hao, Hongyan, Ouyang, Xin, Wang, Simeng, Wang, Yan, Shen, Yue, Gu, Jinjie, Cui, Qing, Li, Longfei, Xue, Siqiao, Zhang, James Y, Li, Sheng
Recent advancements in recommendation systems have shifted towards more comprehensive and personalized recommendations by utilizing large language models (LLM). However, effectively integrating LLM's commonsense knowledge and reasoning abilities into
Externí odkaz:
http://arxiv.org/abs/2308.10837
Autor:
Wang, Yan, Chu, Zhixuan, Ouyang, Xin, Wang, Simeng, Hao, Hongyan, Shen, Yue, Gu, Jinjie, Xue, Siqiao, Zhang, James Y, Cui, Qing, Li, Longfei, Zhou, Jun, Li, Sheng
Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that levera
Externí odkaz:
http://arxiv.org/abs/2308.10835
Autor:
Xue, Siqiao, Shi, Xiaoming, Chu, Zhixuan, Wang, Yan, Hao, Hongyan, Zhou, Fan, Jiang, Caigao, Pan, Chen, Zhang, James Y., Wen, Qingsong, Zhou, Jun, Mei, Hongyuan
Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive mod
Externí odkaz:
http://arxiv.org/abs/2307.08097
Autor:
Shi, Xiaoming, Xue, Siqiao, Wang, Kangrui, Zhou, Fan, Zhang, James Y., Zhou, Jun, Tan, Chenhao, Mei, Hongyuan
Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence models. We desi
Externí odkaz:
http://arxiv.org/abs/2305.16646
In this paper, we tackle the important yet under-investigated problem of making long-horizon prediction of event sequences. Existing state-of-the-art models do not perform well at this task due to their autoregressive structure. We propose HYPRO, a h
Externí odkaz:
http://arxiv.org/abs/2210.01753