Explanipedia

DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Framework Open

Kuiye Ding, Fanda Fan, Yao Wang, Ruijie Jian, Xiaorui Wang , et al. · 2025

Multivariate Time Series Forecasting plays a key role in many applications. Recent works have explored using Large Language Models for MTSF to take advantage of their reasoning abilities. However, many methods treat LLMs as end-to-end fore…

KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting Open

Kuiye Ding, Fanda Fan, Zhaoxiang Wang, Hongxiao Li, Yifan Wang , et al. · 2025

In the World Wide Web, reliable time series forecasts provide the forward-looking signals that drive resource planning, cache placement, and anomaly response, enabling platforms to operate efficiently as user behavior and content distribut…

Patrick Star: A comprehensive benchmark for multi-modal image editing Open

Di Cheng, Zhengxin Yang, Chunjie Luo, Zheng Chen, Yingjie Shi · 2024

Could bibliometrics reveal top science and technology achievements and researchers? The case for evaluatology-based science and technology evaluation Open

Guoxin Kang, Wanling Gao, Lei Wang, Chunjie Luo, Hainan Ye , et al. · 2024

By utilizing statistical methods to analyze bibliographic data, bibliometrics faces inherent limitations in identifying the most significant science and technology achievements and researchers. To overcome this challenge, we present an eva…

Could Bibliometrics Reveal Top Science and Technology Achievements and Researchers? The Case for Evaluatology-based Science and Technology Evaluation Open

Guoxin Kang, Wanling Gao, Lei Wang, Chunjie Luo, Hainan Ye , et al. · 2024

By utilizing statistical methods to analyze bibliographic data, bibliometrics faces inherent limitations in identifying the most significant science and technology achievements and researchers. To overcome this challenge, we present an eva…

DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos Open

Chunjie Luo, Fei Luo, Yusen Wang, Enxu Zhao, Chunxia Xiao · 2024

Reconstructing a dynamic human with loose clothing is an important but difficult task. To address this challenge, we propose a method named DLCA-Recon to create human avatars from monocular videos. The distance from loose clothing to the u…

Evaluatology: The Science and Engineering of Evaluation Open

Jianfeng Zhan, Lei Wang, Wanling Gao, Hongxiao Li, Chenxi Wang , et al. · 2024

Evaluation is a crucial aspect of human existence and plays a vital role in various fields. However, it is often approached in an empirical and ad-hoc manner, lacking consensus on universal concepts, terminologies, theories, and methodolog…

Evaluatology: The science and engineering of evaluation Open

Jianfeng Zhan, Lei Wang, Wanling Gao, Hongxiao Li, Chenxi Wang , et al. · 2024

Evaluation is a crucial aspect of human existence and plays a vital role in each field. However, it is often approached in an empirical and ad-hoc manner, lacking consensus on universal concepts, terminologies, theories, and methodologies.…

AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI Open

Fanda Fan, Chunjie Luo, Jianfeng Zhan, Wanling Gao · 2024

The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to eva…

DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos Open

Chunjie Luo, Fei Luo, Yusen Wang, Enxu Zhao, Chunxia Xiao · 2023

Reconstructing a dynamic human with loose clothing is an important but difficult task. To address this challenge, we propose a method named DLCA-Recon to create human avatars from monocular videos. The distance from loose clothing to the u…

AIGCBench: Comprehensive evaluation of image-to-video content generated by AI Open

Fanda Fan, Chunjie Luo, Wanling Gao, Jianfeng Zhan · 2023

The burgeoning field of Artificial Intelligence Generated Content (AIGC) is witnessing rapid advancements, particularly in video generation. This paper introduces AIGCBench, a pioneering comprehensive and scalable benchmark designed to eva…

Hierarchical Masked 3D Diffusion Model for Video Outpainting Open

Fanda Fan, Chaoxu guo, Litong Gong, Biao Wang, Tiezheng Ge , et al. · 2023

Video outpainting aims to complete missing areas at the edges of video frames adequately. Compared to image outpainting, it presents an additional challenge as the model should maintain the temporal consistency of the filled area. In this …

Hierarchical Masked 3D Diffusion Model for Video Outpainting Open

Fanda Fan, Chaoxu Guo, Litong Gong, Biao Wang, Tiezheng Ge , et al. · 2023

Video outpainting aims to adequately complete missing areas at the edges of video frames. Compared to image outpainting, it presents an additional challenge as the model should maintain the temporal consistency of the filled area. In this …

Design and Research of Power Battery Temperature Control by PLC Open

Chao Cheng, Jian Lin, Haoxiang Zhang, Qian Wang, Lin Xi , et al. · 2023

With the increasingly serious environmental pollution, electric vehicles are more and more favored by people, its power battery temperature control is an important premise to ensure driving safety. At the same time, with the gradual advanc…

WPC: Whole-picture Workload Characterization Open

Lei Wang, Kaiyong Yang, Chenxi Wang, Wanling Gao, Chunjie Luo , et al. · 2023

This article raises an important and challenging workload characterization issue: can we uncover each critical component across the stacks contributing what percentages to any specific bottleneck? The typical critical components include la…

DCNetBench: Scaleable Data Center Network Benchmarking Open

Ke Liu, Wanling Gao, Chunjie Luo, Cheng Zhi Huang, Chunxin Lan , et al. · 2023

Data center networking is the central infrastructure of the modern information society. However, benchmarking them is very challenging as the real-world network traffic is difficult to model, and Internet service giants treat the network t…

Quality at the Tail of Machine Learning Inference Open

Zhengxin Yang, Wanling Gao, Chunjie Luo, Lei Wang, Jianfeng Zhan · 2022

Machine learning inference should be subject to stringent inference time constraints while ensuring high inference quality, especially in safety-critical (e.g., autonomous driving) and mission-critical (e.g., emotion recognition) contexts.…

High fusion computers: The IoTs, edges, data centers, and humans-in-the-loop as a computer Open

Wanling Gao, Lei Wang, Mingyu Chen, Jin Xiong, Chunjie Luo , et al. · 2022

Emerging and future applications rely heavily upon systems consisting of Internet of Things (IoT), edges, data centers, and humans-in-the-loop. Significantly different from warehouse-scale computers that serve independent concurrent user r…

HPC AI500 V3.0: A scalable HPC AI benchmarking framework Open

Zihan Jiang, Chunjie Luo, Wanling Gao, Lei Wang, Jianfeng Zhan · 2022

In recent years, the convergence of High Performance Computing (HPC) and artificial intelligence (AI) makes the community desperately need a benchmark to guide the design of next-generation scalable HPC AI systems. The success of the HPL b…

IoTBench: A data centrical and configurable IoT benchmark suite Open

Simin Chen, Chunjie Luo, Wanling Gao, Lei Wang · 2022

As the Internet of Things (IoT) industry expands, the demand for microprocessors and microcontrollers used in IoT systems has increased steadily. Benchmarks provide a valuable reference for processor evaluation. Different IoT application s…

2022 BenchCouncil International Symposium on benchmarking, measuring and optimizing (Bench 2022) call for papers Open

Chunjie Luo, Wanling Gao · 2022

Sponsored and organized by the International Open Benchmark Council (BenchCouncil), the Bench conference encompasses a wide range of topics in benchmarking, measurement, evaluation methods, and tools. Bench’s multi-disciplinary emphasis pr…

High fusion computers: The IoTs, edges, data centers, and humans-in-the-loop as a computer Open

Wanling Gao, Lei Wang, Mingyu Chen, Jin Xiong, Chunjie Luo , et al. · 2022

Emerging and future applications rely heavily upon systems consisting of Internet of Things (IoT), edges, data centers, and humans-in-the-loop. Significantly different from warehouse-scale computers that serve independent concurrent user r…

Benchmarking feature selection methods with different prediction models on large-scale healthcare event data Open

Fan Zhang, Chunjie Luo, Chuanxin Lan, Jianfeng Zhan · 2021

With the development of the Electronic Health Record (EHR) technique, vast volumes of digital clinical data are generated. Based on the data, many methods are developed to improve the performance of clinical predictions. Among those method…

Shift-and-Balance Attention Open

Chunjie Luo, Jianfeng Zhan, Tianshu Hao, Lei Wang, Wanling Gao · 2021

Attention is an effective mechanism to improve the deep model capability. Squeeze-and-Excite (SE) introduces a light-weight attention branch to enhance the network's representational power. The attention branch is gated using the Sigmoid f…

HPC AI500: Representative, Repeatable and Simple HPC AI Benchmarking Open

Zihan Jiang, Wanling Gao, Fei Tang, Xingwang Xiong, Lei Wang , et al. · 2021

Recent years witness a trend of applying large-scale distributed deep learning algorithms (HPC AI) in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality. The HPC …

An Isolated Data Island Benchmark Suite for Federated Learning. Open

Yuan Liang, Yange Guo, Yanxia Gong, Chunjie Luo, Jianfeng Zhan , et al. · 2020

Federated learning (FL) is a new machine learning paradigm, the goal of which is to build a machine learning model based on data sets distributed on multiple devices--so called Isolated Data Island--while keeping their data secure and priv…

FLBench: A Benchmark Suite for Federated Learning Open

Yuan Liang, Yange Guo, Yanxia Gong, Chunjie Luo, Jianfeng Zhan , et al. · 2020

Federated learning is a new machine learning paradigm. The goal is to build a machine learning model from the data sets distributed on multiple devices so-called an isolated data island, while keeping their data secure and private. Most ex…

HPC AI500: The Methodology, Tools, Roofline Performance Models, and Metrics for Benchmarking HPC AI Systems Open

Zihan Jiang, Lei Wang, Xingwang Xiong, Wanling Gao, Chunjie Luo , et al. · 2020

The recent years witness a trend of applying large-scale distributed deep learning in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality. The HPC community feels …

Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks Open

Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao · 2020

To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN). Different from Batch Normalization (BN), which normalizes the final summation of the weighted inputs, FBN normalizes the intermediate st…

Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices Open

Chunjie Luo, Xiwen He, Jianfeng Zhan, Lei Wang, Wanling Gao , et al. · 2020

Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains. The application of deep learning on the mobile and embedded devices is taken more and more attentions, benchmarking and rank…

Chunjie Luo YOU? Author Swipe