Explanipedia

From PBFT to the present: a thorough overview of blockchain consensus protocols Open

Xiang Fu, Huaimin Wang, Keming Wang, Feng Jiang · 2025

Empowering Large Language Model Agent through Step-Level Self-Critique and Self-Training Open

Yuanzhao Zhai, Huanxi Liu, Zhuo Zhang, Tong Lin, Kele Xu , et al. · 2025

Towards Understanding Docker Build Faults in Practice: Symptoms, Root Causes, and Fix Patterns Open

Yiwen Wu, Yang Zhang, Tao Wang, Bo Ding, Huaimin Wang · 2025

Docker building is a critical component of containerization in modern software development, automating the process of packaging and converting sources into container images. It is not uncommon to find that Docker build faults (DBFs) occur …

Joint$λ$: Orchestrating Serverless Workflows on Jointcloud FaaS Systems Open

Jianfei Liu, Rui Li, Zhilin Yang, Peichang Shi, Grace Y. Yi , et al. · 2025

Existing serverless workflow orchestration systems are predominantly designed for a single-cloud FaaS system, leading to vendor lock-in. This restricts performance optimization, cost reduction, and availability of applications. However, or…

Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models Open

Ying Zhai, Tingkai Yang, Kele Xu, Deqiang Feng, Cheng Yang , et al. · 2025

Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple decision…

Software Engineering for OpenHarmony: A Research Roadmap Open

Li Li, Xiang Gao, Hailong Sun, Chunming Hu, Xiaoyu Sun , et al. · 2025

Mobile software engineering has been a hot research topic for decades. Our fellow researchers have proposed various approaches (with over 7,000 publications for Android alone) in this field that essentially contributed to the great success…

NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing Open

Fei Gao, Ming Hu, Zhicheng Xie, Peichang Shi, Xiaofei Xie , et al. · 2024

With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud Computing (JCC) is promising to break through the resource constraints caused by heteroge…

Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models Open

Ying Zhai, Tingkai Yang, Kele Xu, Feng Dawei, Cheng Yang , et al. · 2024

Agents significantly enhance the capabilities of standalone Large Language Models (LLMs) by perceiving environments, making decisions, and executing actions. However, LLM agents still face challenges in tasks that require multiple decision…

Online Self-Preferring Language Models Open

Yuanzhao Zhai, Zhuo Zhang, Kele Xu, Hanyang Peng, Yue Yu , et al. · 2024

Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward model to provide feedback for on-policy sampling responses.…

A Transformer-based Model for Assisting Dockerfile Revising Open

Yiwen Wu, Yang Zhang, Tao Wang, Huaimin Wang · 2024

Dockerfile plays an important role in the containerized software development process since it specifies the structure and functionality of the built Docker image. Currently, Dockerfile writing and modification still rely on manual operatio…

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization Open

Yuanzhao Zhai, Yiying Li, Zijian Gao, Xudong Gong, Kele Xu , et al. · 2024

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy opti…

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization Open

Yuanzhao Zhai, Yiying Li, Zijian Gao, Xudong Gong, Kele Xu , et al. · 2024

Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works primarily focus on incorporating pessimism for policy opti…

Development Strategy of Collective Intelligence and Its Industrial Clusters Open

Wenjun Wu, Zhiming Zheng, Huaimin Wang, Shaoting Tang, Tao Wang · 2024

Collective intelligence is an important component of the new generation of artificial intelligence (AI). It plays a decisive role in stimulating and converging innovative forces as well as coupling and integrating large-scale intelligent s…

Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles Open

Yuanzhao Zhai, Han Zhang, Lei Yu, Yue Yu, Kele Xu , et al. · 2023

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher …

Software Engineering for OpenHarmony: A Research Roadmap Open

Li Li, Xiang Gao, Hailong Sun, Chunming Hu, Xiaoyu Sun , et al. · 2023

Mobile software engineering has been a hot research topic for decades. Our fellow researchers have proposed various approaches (with over 7,000 publications for Android alone) in this field that essentially contributed to the great success…

Ark Filter: A General and Space-Efficient Sketch for Network Flow Analysis Open

Lailong Luo, Pengtao Fu, Shangsen Li, Deke Guo, Qianzhen Zhang , et al. · 2023

Sketches are widely deployed to represent network flows to support complex flow analysis. Typical sketches usually employ hash functions to map elements into a hash table or bit array. Such sketches still suffer from potential weaknesses u…

Jump Filter: A Dynamic Sketch for Big Data Governance Open

Pengtao Fu, Lailong Luo, Deke Guo, Xiang Zhao, Shangsen Li , et al. · 2023

Intelligent Computing: The Latest Advances, Challenges, and Future Open

Shiqiang Zhu, Ting Yu, Tao Xu, Hongyang Chen, Schahram Dustdar , et al. · 2023

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digit…

Intelligent Computing: The Latest Advances, Challenges and Future Open

Shiqiang Zhu, Ting Yu, Tao Xu, Hongyang Chen, Schahram Dustdar , et al. · 2022

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digit…

pull request id for the dataset of "Pull Request Latency Explained: An Empirical Overview" Open

Xunhui Zhang, Yue Yu, Tao Wang, Ayushi Rastogi, Huaimin Wang · 2022

This is used for research, which includes the pull request id. Researchers need to request the access.

pull request id for the dataset of "Pull Request Latency Explained: An Empirical Overview" Open

Xunhui Zhang, Yue Yu, Tao Wang, Ayushi Rastogi, Huaimin Wang · 2022

This is used for research, which includes the pull request id. Researchers need to request the access.

Understanding and Predicting Docker Build Duration: An Empirical Study of Containerized Workflow of OSS Projects Open

Yiwen Wu, Yang Zhang, Kele Xu, Tao Wang, Huaimin Wang · 2022

Docker building is a critical component of containerized workflow, which automates the process by which sources are packaged and transformed into container images. If not run properly, Docker builds can bring long durations (i.e., slow bui…

Dynamic Memory-based Curiosity: A Bootstrap Approach for Exploration Open

Zijian Gao, Kele Xu, Yiying Li, Yuanzhao Zhai, Dawei Feng , et al. · 2022

The sparsity of extrinsic rewards poses a serious challenge for reinforcement learning (RL). Currently, many efforts have been made on curiosity which can provide a representative intrinsic reward for effective exploration. However, the ch…

Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning Open

Zijian Gao, Kele Xu, HengXing Cai, Yuanzhao Zhai, Dawei Feng , et al. · 2022

Under sparse extrinsic reward settings, reinforcement learning has remained challenging, despite surging interests in this field. Previous attempts suggest that intrinsic reward can alleviate the issue caused by sparsity. In this article, …

Diversifying Message Aggregation in Multi-Agent Communication via Normalized Tensor Nuclear Norm Regularization Open

Yuanzhao Zhai, Kele Xu, Bo Ding, Dawei Feng, Zijian Gao , et al. · 2022

Aggregating messages is a key component for the communication of multi-agent reinforcement learning (Comm-MARL). Recently, it has witnessed the prevalence of graph attention networks (GAT) in Comm-MARL, where agents can be represented as n…

Trusted Multi-Scale Classification Framework for Whole Slide Image Open

Feng Ming, Kele Xu, Nanhui Wu, Weiquan Huang, Yan Bai , et al. · 2022

Despite remarkable efforts been made, the classification of gigapixels whole-slide image (WSI) is severely restrained from either the constrained computing resources for the whole slides, or limited utilizing of the knowledge from differen…

Pull request latency explained: an empirical overview Open

Xunhui Zhang, Yue Yu, Tao Wang, Ayushi Rastogi, Huaimin Wang · 2022

Nuclear Norm Maximization Based Curiosity-Driven Learning Open

Chao Chen, Zijian Gao, Kele Xu, Sen Yang, Yiying Li , et al. · 2022

To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in handy for pursuing the rewards in the future, such as enco…

Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast Open

Boqing Zhu, Kele Xu, Changjian Wang, Zheng Qin, Tong Sun , et al. · 2022

We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These met…

The Development and Prospect of Code Clone Open

Xunhui Zhang, Tao Wang, Yue Yu, Yanzhi Zhang, Yan Zhong , et al. · 2022

The application of code clone technology accelerates code search, improves code reuse efficiency, and assists in software quality assessment and code vulnerability detection. However, the application of code clones also introduces software…

Huaimin Wang YOU? Author Swipe