43 citations · 129 across the 62 of their papers we have counts for
19 papers · 1 filter
REFA: Reference Free Alignment for multi-preference optimization
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +2
To mitigate reward hacking from response verbosity, modern preference optimization methods are increasingly adopting length normalization (e.g., SimPO, ORPO, LN-DPO). While effecti…
Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +3
Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy…
Ensuring Fair LLM Serving Amid Diverse Applications
Redwan Ibne Seraj Khan, Kunal Jain, Haiying Shen +12
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 una…
Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC
Aditya Soni, Mayukh Das, Anjaly Parayil +8
The difficulty of exploring and training online on real production systems limits the scope of real-time online data/feedback-driven decision making. The most feasible approach is…
CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
Taneesh Gupta, Shivam Shandilya, Xuchao Zhang +5
Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily…
CREAM: Consistency Regularized Self-Rewarding Language Models
Zhaoyang Wang, Weilei He, Zhiyuan Liang +5
Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations fo…
Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing
Kunal Jain, Anjaly Parayil, Ankur Mallick +10
Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling in…
Building AI Agents for Autonomous Clouds: Challenges and Design Principles
Manish Shetty, Yinfang Chen, Gagan Somashekar +10
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. Wh…
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Peng Xia, Ze Chen, Juanxi Tian +21
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the…
Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection
Jun Liu, Chaoyun Zhang, Jiaxu Qian +6
Time series anomaly detection (TSAD) plays a crucial role in various industries by identifying atypical patterns that deviate from standard trends, thereby maintaining system integ…
Towards Cloud Efficiency with Large-scale Workload Characterization
Anjaly Parayil, Jue Zhang, Xiaoting Qin +4
Cloud providers introduce features (e.g., Spot VMs, Harvest VMs, and Burstable VMs) and optimizations (e.g., oversubscription, auto-scaling, power harvesting, and overclocking) to…
Workload Intelligence: Punching Holes Through the Cloud Abstraction
Lexiang Huang, Anjaly Parayil, Jue Zhang +13
Today, cloud workloads are essentially opaque to the cloud platform. Typically, the only information the platform receives is the virtual machine (VM) type and possibly a decoratio…
X-lifecycle Learning for Cloud Incident Management using LLMs
Drishti Goel, Fiza Husain, Aditya Singh +5
Incident management for large cloud services is a complex and tedious process and requires significant amount of manual efforts from on-call engineers (OCEs). OCEs typically levera…
Exploring LLM-based Agents for Root Cause Analysis
Devjeet Roy, Xuchao Zhang, Rashi Bhave +4
The growing complexity of cloud based software systems has resulted in incident management becoming an integral part of the software development lifecycle. Root cause analysis (RCA…
Intelligent Monitoring Framework for Cloud Services: A Data-Driven Approach
Pooja Srinivas, Fiza Husain, Anjaly Parayil +3
Cloud service owners need to continuously monitor their services to ensure high availability and reliability. Gaps in monitoring can lead to delay in incident detection and signifi…
Dependency Aware Incident Linking in Large Cloud Systems
Supriyo Ghosh, Karish Grover, Jimmy Wong +4
Despite significant reliability efforts, large-scale cloud services inevitably experience production incidents that can significantly impact service availability and customer's sat…
Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4
Xuchao Zhang, Supriyo Ghosh, Chetan Bansal +4
Root Cause Analysis (RCA) plays a pivotal role in the incident diagnosis process for cloud services, requiring on-call engineers to identify the primary issues and implement correc…
COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
Lu Wang, Mayukh Das, Fangkai Yang +9
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…
Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning
Lu Wang, Mayukh Das, Fangkai Yang +11
Oversubscription is a prevalent practice in cloud services where the system offers more virtual resources, such as virtual cores in virtual machines, to users or applications than…