Saravan Rajmohan

Orcid: 0009-0003-0204-7187

According to our database1, Saravan Rajmohan authored at least 76 papers between 2022 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Token-level Proximal Policy Optimization for Query Generation.
CoRR, 2024

Self-Evolved Reward Learning for LLMs.
CoRR, 2024

Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks.
CoRR, 2024

Unveiling Context-Aware Criteria in Self-Assessing LLMs.
CoRR, 2024

Turn Every Application into an Agent: Towards Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents.
CoRR, 2024

Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Scheduling.
CoRR, 2024

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

The Vision of Autonomic Computing: Can LLMs Make It a Reality?
CoRR, 2024

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

An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing.
CoRR, 2024

Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection.
CoRR, 2024

Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers.
CoRR, 2024

Workload Intelligence: Punching Holes Through the Cloud Abstraction.
CoRR, 2024

AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models.
CoRR, 2024

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

UFO: A UI-Focused Agent for Windows OS Interaction.
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

COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy.
CoRR, 2024

Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning.
CoRR, 2024

Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective.
Proceedings of the ACM on Web Conference 2024, 2024

Dependency Aware Incident Linking in Large Cloud Systems.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2024, 2024

LM-PACE: Confidence Estimation by Large Language Models for Effective Root Causing of Cloud Incidents.
Proceedings of the Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, 2024

Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4.
Proceedings of the Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, 2024

MonitorAssistant: Simplifying Cloud Service Monitoring via Large Language Models.
Proceedings of the Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, 2024

Exploring LLM-Based Agents for Root Cause Analysis.
Proceedings of the Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, 2024

X-Lifecycle Learning for Cloud Incident Management using LLMs.
Proceedings of the Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering, 2024

Pre-trained KPI Anomaly Detection Model Through Disentangled Transformer.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Large Language Models Can Provide Accurate and Interpretable Incident Triage.
Proceedings of the 35th IEEE International Symposium on Software Reliability Engineering, 2024

Early Bird: Ensuring Reliability of Cloud Systems Through Early Failure Prediction.
Proceedings of the 35th IEEE International Symposium on Software Reliability Engineering, 2024

Can We Trust Auto-Mitigation? Improving Cloud Failure Prediction with Uncertain Positive Learning.
Proceedings of the 35th IEEE International Symposium on Software Reliability Engineering, 2024

UniLog: Automatic Logging via LLM and In-Context Learning.
Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, 2024

Intelligent Monitoring Framework for Cloud Services: A Data-Driven Approach.
Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice, 2024

Xpert: Empowering Incident Management with Query Recommendations via Large Language Models.
Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, 2024

Automatic Root Cause Analysis via Large Language Models for Cloud Incidents.
Proceedings of the Nineteenth European Conference on Computer Systems, 2024

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, 2024

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 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

Building AI Agents for Autonomous Clouds: Challenges and Design Principles.
Proceedings of the 2024 ACM Symposium on Cloud Computing, 2024

COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty.
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection.
Proc. VLDB Endow., November, 2023

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

Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective.
CoRR, 2023

PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis.
CoRR, 2023

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

Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance.
CoRR, 2023

Empowering Practical Root Cause Analysis by Large Language Models for Cloud Incidents.
CoRR, 2023

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

Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning.
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

Multi-Agent Reinforcement Learning with Shared Policy for Cloud Quota Management Problem.
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

STEAM: Observability-Preserving Trace Sampling.
Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023

TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems.
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

Root Cause Analysis for Microservice Systems via Hierarchical Reinforcement Learning from Human Feedback.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

CODEC: Cost-Effective Duration Prediction System for Deadline Scheduling in the Cloud.
Proceedings of the 34th IEEE International Symposium on Software Reliability Engineering, 2023

TraceArk: Towards Actionable Performance Anomaly Alerting for Online Service Systems.
Proceedings of the 45th IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, 2023

Incident-aware Duplicate Ticket Aggregation for Cloud Systems.
Proceedings of the 45th IEEE/ACM International Conference on Software Engineering, 2023

CONAN: Diagnosing Batch Failures for Cloud Systems.
Proceedings of the 45th IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, 2023

Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models.
Proceedings of the 45th IEEE/ACM International Conference on Software Engineering, 2023

Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection.
Proceedings of the Eleventh International Conference on Learning Representations, 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

How Different are the Cloud Workloads? Characterizing Large-Scale Private and Public Cloud Workloads.
Proceedings of the 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Network, 2023

Snape: Reliable and Low-Cost Computing with Mixture of Spot and On-Demand VMs.
Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2023

2022
An Intelligent Framework for Timely, Accurate, and Comprehensive Cloud Incident Detection.
ACM SIGOPS Oper. Syst. Rev., 2022

Spot Virtual Machine Eviction Prediction in Microsoft Cloud.
Proceedings of the Companion of The Web Conference 2022, Virtual Event / Lyon, France, April 25, 2022

UniParser: A Unified Log Parser for Heterogeneous Log Data.
Proceedings of the WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, April 25, 2022

Solving the Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach.
Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 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


  Loading...