Pu Zhao

Orcid: 0000-0002-4518-323X

Affiliations:
  • Microsoft Research, China


According to our database1, Pu Zhao authored at least 46 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation.
CoRR, 2024

Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena.
CoRR, 2024

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation.
CoRR, 2024

Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides.
CoRR, 2024

Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction.
CoRR, 2024

Contrastive Learning with Negative Sampling Correction.
CoRR, 2024

SOIL: Score Conditioned Diffusion Model for Imbalanced Cloud Failure Prediction.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2024, 2024

SELF-GUARD: Empower the LLM to Safeguard Itself.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

WizardCoder: Empowering Code Large Language Models with Evol-Instruct.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides.
Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023
TaskWeaver: A Code-First Agent Framework.
CoRR, 2023

Diffusion-based Time Series Data Imputation for Microsoft 365.
CoRR, 2023

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.
CoRR, 2023

Introspective Tips: Large Language Model for In-Context Decision Making.
CoRR, 2023

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering.
CoRR, 2023

Augmented Large Language Models with Parametric Knowledge Guiding.
CoRR, 2023

WizardLM: Empowering Large Language Models to Follow Complex Instructions.
CoRR, 2023

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval.
CoRR, 2023

HAPENS: Hardness-Personalized Negative Sampling for Implicit Collaborative Filtering.
Proceedings of the Companion Proceedings of the ACM Web Conference 2023, 2023

EDITS: An Easy-to-difficult Training Strategy for Cloud Failure Prediction.
Proceedings of the Companion Proceedings of the ACM Web Conference 2023, 2023

Diffusion-Based Time Series Data Imputation for Cloud Failure Prediction at Microsoft 365.
Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023

Assess and Summarize: Improve Outage Understanding with Large Language Models.
Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023

Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: EMNLP 2023, 2023

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022
An empirical investigation of missing data handling in cloud node failure prediction.
Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2022

NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365.
Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Multi-task Hierarchical Classification for Disk Failure Prediction in Online Service Systems.
Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification.
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

2021
NTAM: Neighborhood-Temporal Attention Model for Disk Failure Prediction in Cloud Platforms.
Proceedings of the WWW '21: The Web Conference 2021, 2021

Fighting the Fog of War: Automated Incident Detection for Cloud Systems.
Proceedings of the 2021 USENIX Annual Technical Conference, 2021

Effective low capacity status prediction for cloud systems.
Proceedings of the ESEC/FSE '21: 29th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2021

RLNF: Reinforcement Learning based Noise Filtering for Click-Through Rate Prediction.
Proceedings of the SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021

How Long Will it Take to Mitigate this Incident for Online Service Systems?
Proceedings of the 32nd IEEE International Symposium on Software Reliability Engineering, 2021

Fast Outage Analysis of Large-scale Production Clouds with Service Correlation Mining.
Proceedings of the 43rd IEEE/ACM International Conference on Software Engineering, 2021

AutoCCAG: An Automated Approach to Constrained Covering Array Generation.
Proceedings of the 43rd IEEE/ACM International Conference on Software Engineering, 2021

PULNS: Positive-Unlabeled Learning with Effective Negative Sample Selector.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Correlation-Aware Heuristic Search for Intelligent Virtual Machine Provisioning in Cloud Systems.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
How to mitigate the incident? an effective troubleshooting guide recommendation technique for online service systems.
Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Efficient customer incident triage via linking with system incidents.
Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Identifying linked incidents in large-scale online service systems.
Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Towards intelligent incident management: why we need it and how we make it.
Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Predictive and Adaptive Failure Mitigation to Avert Production Cloud VM Interruptions.
Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation, 2020

Intelligent Virtual Machine Provisioning in Cloud Computing.
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020


  Loading...