Search Results for author:
Found 59 papers, 13 papers with code
Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
Our method generates pseudo-rewards through a self-supervised mechanism that leverages the inherent structure of both teacher and student responses, enabling reward learning without explicit external evaluation.
AMPO: Active Multi-Preference Optimization
In this work, we propose $\textit{Active Multi-Preference Optimization}$ (AMPO), a novel approach that combines on-policy generation, a multi-preference group-contrastive loss, and active subset selection.
Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance
Proximal Policy Optimization (PPO)-based Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human preferences.
MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our Behalf
In contemporary workplaces, meetings are essential for exchanging ideas and ensuring team alignment but often face challenges such as time consumption, scheduling conflicts, and inefficient participation.
Enabling Autonomic Microservice Management through Self-Learning Agents
The increasing complexity of modern software systems necessitates robust autonomic self-management capabilities.
Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
The advancement of large language models has intensified the need to modernize enterprise applications and migrate legacy systems to secure, versatile languages.
DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale
Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and external packages required for a repository to successfully run.
AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds
AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact.
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models
Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges for data collection and annotation.
REFA: Reference Free Alignment for multi-preference optimization
We introduce REFA, a family of reference-free alignment methods that optimize over multiple user preferences while enforcing fine-grained length control.
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning to obtain a target description.
Large Action Models: From Inception to Implementation
As AI continues to advance, there is a growing demand for systems that go beyond language-based assistance and move toward intelligent agents capable of performing real-world actions.
TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
Our solution introduces two key innovations: FlashQ, a headwise attention quantization technique that enables both compression of KV cache and quantized execution of activation-activation multiplication, and Sparsity-based Softmax Approximation (SAS), which eliminates the need for dequantization to FP32 during exponentiation operation in attention.
SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment
We introduce Simultaneous Weighted Preference Optimization (SWEPO), a novel extension of Direct Preference Optimization (DPO) designed to accommodate multiple dynamically chosen positive and negative responses for each query.
Large Language Model-Brained GUI Agents: A Survey
This has paved the way for a new generation of LLM-brained GUI agents capable of interpreting complex GUI elements and autonomously executing actions based on natural language instructions.
Ensuring Fair LLM Serving Amid Diverse Applications
In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness.
Sharingan: Extract User Action Sequence from Desktop Recordings
Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes.
RuAG: Learned-rule-augmented Generation for Large Language Models
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection.
Self-Evolved Reward Learning for LLMs
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2.
Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks
The rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks.
Unveiling Context-Aware Criteria in Self-Assessing LLMs
The use of large language models (LLMs) as evaluators has garnered significant attention due to their potential to rival human-level evaluations in long-form response assessments.
AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces.
Turn Every Application into an Agent: Towards Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
This framework also facilitates the creation and expansion of APIs through automated exploration of applications.
EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries.
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Moreover, to increase the difficulty diversity of generated planning tasks, we propose a bidirectional evolution method, Bi-Evol, that evolves planning tasks from easier and harder directions to synthesize a task set with a smoother difficulty curve.
The Vision of Autonomic Computing: Can LLMs Make It a Reality?
The Vision of Autonomic Computing (ACV), proposed over two decades ago, envisions computing systems that self-manage akin to biological organisms, adapting seamlessly to changing environments.
Building AI Agents for Autonomous Clouds: Challenges and Design Principles
The rapid growth in the use of Large Language Models (LLMs) and AI Agents as part of software development and deployment is revolutionizing the information technology landscape.
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) systems.
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Recent advances in retrieval-augmented generation have significantly improved the performance of question-answering systems, particularly on factoid '5Ws' questions.
An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing
Efficient resource utilization and perfect user experience usually conflict with each other in cloud computing platforms.
Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection
Time series anomaly detection (TSAD) plays a crucial role in various industries by identifying atypical patterns that deviate from standard trends, thereby maintaining system integrity and enabling prompt response measures.
Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers
We identify that the associative property of online softmax can be treated as a reduction operation thus allowing us to parallelize the attention computation over these large context lengths.
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
We propose Reasoning-Path-Editing (Readi), a novel framework where LLMs can efficiently and faithfully reason over structured environments.
Exploring LLM-based Agents for Root Cause Analysis
Lastly, we conduct a case study with a team at Microsoft to equip the ReAct agent with tools that give it access to external diagnostic services that are used by the team for manual RCA.
Intelligent Monitoring Framework for Cloud Services: A Data-Driven Approach
We conduct an extensive empirical study and derive key insights on the major classes of monitors employed by cloud services at Microsoft, their associated dimensions, and the interrelationship between service properties and this ontology.
Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides
Effective incident management is pivotal for the smooth operation of enterprises-level cloud services.
X-lifecycle Learning for Cloud Incident Management using LLMs
to generate insights for detection, root causing and mitigating of incidents.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective
To ensure an accurate AD, FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) to significantly increase the accuracy of reconstructing the normal data.
Dependency Aware Incident Linking in Large Cloud Systems
In this paper, we propose the dependency-aware incident linking (DiLink) framework which leverages both textual and service dependency graph information to improve the accuracy and coverage of incident links not only coming from same service, but also from different services and workloads.
Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4
The results reveal that our in-context learning approach outperforms the previous fine-tuned large language models such as GPT-3 by an average of 24. 8\% across all metrics, with an impressive 49. 7\% improvement over the zero-shot model.
Contrastive Learning with Negative Sampling Correction
To correct the negative sampling bias, we propose a novel contrastive learning method named Positive-Unlabeled Contrastive Learning (PUCL).
COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against resource congestion risk.
Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.
Xpert: Empowering Incident Management with Query Recommendations via Large Language Models
This paper presents a thorough empirical study on the utilization of queries of KQL, a DSL employed for incident management in a large-scale cloud management system at Microsoft.
TaskWeaver: A Code-First Agent Framework
TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
In this paper, we take an information flow control perspective to describe machine learning systems, which allows us to leverage metadata such as access control policies and define clear-cut privacy and confidentiality guarantees with interpretable information flows.
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
To address these limitations, we introduce a novel thought prompting approach called "Everything of Thoughts" (XoT) to defy the law of "Penrose triangle of existing thought paradigms.
PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis
Major cloud providers have employed advanced AI-based solutions like large language models to aid humans in identifying the root causes of cloud incidents.
Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction
Large language models (LLMs) enhanced with retrieval augmentation has shown great performance in many applications.
Diffusion-based Time Series Data Imputation for Microsoft 365
However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance.
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first.
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
To the best of our knowledge, ImDiffusion represents a pioneering approach that combines imputation-based techniques with time series anomaly detection, while introducing the novel use of diffusion models to the field.
Introspective Tips: Large Language Model for In-Context Decision Making
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge.
Conservative State Value Estimation for Offline Reinforcement Learning
In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalty on OOD states.
Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models
In this work, we do the first large-scale study to evaluate the effectiveness of these models for helping engineers root cause and mitigate production incidents.
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
To address these two limitations, this paper formulates the oversubscription for cloud as a chance-constrained optimization problem and propose an effective Chance Constrained Multi-Agent Reinforcement Learning (C2MARL) method to solve this problem.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Solving the Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach
This paper investigates a critical resource allocation problem in the first party cloud: scheduling containers to machines.
