Search Results for author: Siqiao Xue

Found 22 papers, 13 papers with code

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

no code implementations18 Jun 2024 Fan Zhou, Chen Pan, Lintao Ma, Yu Liu, James Zhang, Jun Zhou, Hongyuan Mei, Weitao Lin, Zi Zhuang, Wenxin Ning, Yunhua Hu, Siqiao Xue

These methods merely take the temporal hierarchical structure to maintain coherence without improving the forecasting accuracy.

Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models

1 code implementation7 May 2024 Zhixuan Chu, Lei Zhang, Yichen Sun, Siqiao Xue, Zhibo Wang, Zhan Qin, Kui Ren

Leveraging the state-of-the-art keyframe extraction techniques and multimodal large language models, SoraDetector first evaluates the consistency between extracted video content summary and textual prompts, then constructs static and dynamic knowledge graphs (KGs) from frames to detect hallucination both in single frames and across frames.

Hallucination Knowledge Graphs

Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt

1 code implementation19 Oct 2023 Gangwei Jiang, Caigao Jiang, Siqiao Xue, James Y. Zhang, Jun Zhou, Defu Lian, Ying WEI

In this work, we first investigate such anytime fine-tuning effectiveness of existing continual pre-training approaches, concluding with unanimously decreased performance on unseen domains.

Transfer Learning

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook

5 code implementations16 Oct 2023 Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, XiaoLi Li, Shirui Pan, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong

In this survey, we offer a comprehensive and up-to-date review of large models tailored (or adapted) for time series and spatio-temporal data, spanning four key facets: data types, model categories, model scopes, and application areas/tasks.

Time Series Time Series Analysis

Deep Optimal Timing Strategies for Time Series

1 code implementation9 Oct 2023 Chen Pan, Fan Zhou, Xuanwei Hu, Xinxin Zhu, Wenxin Ning, Zi Zhuang, Siqiao Xue, James Zhang, Yunhua Hu

Deciding the best future execution time is a critical task in many business activities while evolving time series forecasting, and optimal timing strategy provides such a solution, which is driven by observed data.

Probabilistic Time Series Forecasting Time Series

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending

1 code implementation15 Sep 2023 Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li

In fact, anomalous behaviors harming long context extrapolation exist between Rotary Position Embedding (RoPE) and vanilla self-attention unveiled by our work.

2k Position

Continual Learning in Predictive Autoscaling

no code implementations29 Jul 2023 Hongyan Hao, Zhixuan Chu, Shiyi Zhu, Gangwei Jiang, Yan Wang, Caigao Jiang, James Zhang, Wei Jiang, Siqiao Xue, Jun Zhou

In order to surmount this challenge and effectively integrate new sample distribution, we propose a density-based sample selection strategy that utilizes kernel density estimation to calculate sample density as a reference to compute sample weight, and employs weight sampling to construct a new memory set.

Continual Learning Density Estimation

EasyTPP: Towards Open Benchmarking Temporal Point Processes

1 code implementation16 Jul 2023 Siqiao Xue, Xiaoming Shi, Zhixuan Chu, Yan Wang, Hongyan Hao, Fan Zhou, Caigao Jiang, Chen Pan, James Y. Zhang, Qingsong Wen, Jun Zhou, Hongyuan Mei

In this paper, we present EasyTPP, the first central repository of research assets (e. g., data, models, evaluation programs, documentations) in the area of event sequence modeling.

Benchmarking Point Processes

Automatic Deduction Path Learning via Reinforcement Learning with Environmental Correction

no code implementations16 Jun 2023 Shuai Xiao, Chen Pan, Min Wang, Xinxin Zhu, Siqiao Xue, Jing Wang, Yunhua Hu, James Zhang, Jinghua Feng

To this end, we formulate the problem as a partially observable Markov decision problem (POMDP) and employ an environment correction algorithm based on the characteristics of the business.

Hierarchical Reinforcement Learning reinforcement-learning

A Graph Regularized Point Process Model For Event Propagation Sequence

no code implementations21 Nov 2022 Siqiao Xue, Xiaoming Shi, Hongyan Hao, Lintao Ma, Shiyu Wang, Shijun Wang, James Zhang

Point process is the dominant paradigm for modeling event sequences occurring at irregular intervals.

HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences

3 code implementations4 Oct 2022 Siqiao Xue, Xiaoming Shi, james Y zhang, Hongyuan Mei

In this paper, we tackle the important yet under-investigated problem of making long-horizon prediction of event sequences.

Learning Large-scale Universal User Representation with Sparse Mixture of Experts

no code implementations11 Jul 2022 Caigao Jiang, Siqiao Xue, James Zhang, Lingyue Liu, Zhibo Zhu, Hongyan Hao

However, unlike natural language processing (NLP) tasks, the parameters of user behaviour model come mostly from user embedding layer, which makes most existing works fail in training a universal user embedding of large scale.

A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud

1 code implementation31 May 2022 Siqiao Xue, Chao Qu, Xiaoming Shi, Cong Liao, Shiyi Zhu, Xiaoyu Tan, Lintao Ma, Shiyu Wang, Shijun Wang, Yun Hu, Lei Lei, Yangfei Zheng, Jianguo Li, James Zhang

Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud.

Decision Making Management +3

Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes

1 code implementation29 Jan 2022 Chao Qu, Xiaoyu Tan, Siqiao Xue, Xiaoming Shi, James Zhang, Hongyuan Mei

We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized.

Decision Making Model-based Reinforcement Learning +3

Temporal Convolutional Attention-based Network For Sequence Modeling

1 code implementation28 Feb 2020 Hongyan Hao, Yan Wang, Siqiao Xue, Yudi Xia, Jian Zhao, Furao Shen

So we propose an exploratory architecture referred to Temporal Convolutional Attention-based Network (TCAN) which combines temporal convolutional network and attention mechanism.

Cannot find the paper you are looking for? You can Submit a new open access paper.