TBD

Irene Zhang (Microsoft Research)

Hops: Fine-grained heterogeneous sensing, efficient and fair Deep Learning cluster scheduling system

Queue Management for SLO-Oriented Large Language Model Serving

KALE: Elastic GPU Scheduling for Online DL Model Training

FedCaSe: Enhancing Federated Learning with Heterogeneity-aware Caching and Scheduling

SQLStateGuard: Statement-Level SQL Injection Defense Based on Learning-Driven Middleware

Vista: Machine Learning based Database Performance Troubleshooting Framework in Amazon RDS

Building AI Agents for Autonomous Clouds: Challenges and Design Principles

Zero-SAD: Zero-Shot Learning Using Synthetic Abnormal Data for Abnormal Behavior Detection on Private Cloud

Forecasting Algorithms for Intelligent Resource Scaling: An Experimental Analysis

Snapipeline: Accelerating Snapshot Startup for FaaS Containers

En4S: Enabling SLOs in Serverless Storage Systems

Pre-Warming is Not Enough: Accelerating Serverless Inference With Opportunistic Pre-Loading

Faascale: Scaling MicroVM Vertically for Serverless Computing with Memory Elasticity

Rethinking Networking Stack for Serverless Environments: A Sidecar Approach

Process-as-a-Service: Unifying Elastic and Stateful Clouds with Serverless Processes

AutoBurst: Autoscaling Burstable Instances for Cost-effective Latency SLOs

Is It Time To Put Cold Starts In The Deep Freeze?

Towards Swap-Free, Continuous Ballooning for Fast, Cloud-Based Virtual Machine Migrations

PCLive: Pipelined Restoration of Application Containers for Reduced Service Downtime

Scheduling for Reduced Tail Task Latencies in Highly Utilized Datacenters

Krios: Scheduling Abstractions and Mechanisms for Enabling a LEO Compute Cloud

Demystifying the Fight Against Complexity: A Comprehensive Study of Live Debugging Activities in Production Cloud Systems

Deoxys: A Causal Inference Engine for Unhealthy Node Mitigation in Large-scale Cloud Infrastructure

INS:Identifying and Mitigating Performance Interference in Clouds via Interference-Sensitive Paths

TailClipper: Reducing Tail Response Time of Distributed Services Through System-Wide Scheduling

On-demand and Parallel Checkpoint/Restore for GPU Applications

Shared Mixture of Experts

FaPES: Enabling Efficient Elastic Scaling for Serverless Machine Learning Platforms

KACE: Kernel-Aware Colocation for Efficient GPU Sharing

Pack: Towards Communication-Efficient Homomorphic Encryption in Federated Learning

InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment

CDN-Shifter: Leveraging Spatial Workload Shifting to Decarbonize Content Delivery Networks

Accountable Carbon Footprints and Energy Profiling For Serverless Functions

The Sunk Carbon Fallacy: Rethinking Carbon Footprint Metrics for Effective Carbon-Aware Scheduling

Exploring the Efficiency of Renewable Energy-based Modular Data Centers at Scale

The Hidden Carbon Footprint of Serverless Computing

uIO: Lightweight and Extensible Unikernels

Racos: Improving Erasure Coding State Machine Replication using Leaderless Consensus

Occam’s Razor for Distributed Protocols

VWeiST: A Scalable and Efficient Proof-of-Stake Blockchain Consensus

Securing a Multiprocessor KVM Hypervisor with Rust

SURE: Secure Unikernels Make Serverless Computing Rapid and Efficient

TBD

Anastasia Ailamaki (EPFL)

TianMen: a DPU-based storage network offloading structure for disaggregated datacenters

H2C-Dedup: Reducing I/O and GC Amplification for QLC SSDs from the Deduplication Metadata Perspective

RomeFS: A CXL-SSD Aware File System Exploiting Synergy of Memory-Block Dual Paths

SmartGraph: A Framework for Graph Processing in Computational Storage

ConMonitor: Lightweight Container Protection with Virtualization and VM Functions

ByteMQ: A Cloud-native Streaming Data Layer in ByteDance

Dynamic Idle Resource Leasing To Safely Oversubscribe Capacity At Meta

Byways: High-Performance, Isolated Network Functions for Multi-Tenant Cloud Servers

Cloud-native Workflow Scheduling using a Hybrid Priority Rule, Dynamic Resource Allocation, and Dynamic Task Partition

Streamlining Cloud-Native Application Development and Deployment with Robust Encapsulation

Komet: A Serverless Platform for Low-Earth Orbit Edge Services

A Data Optimizer for Region-Aware Self-describing Files in Scientific Computing

Rethinking State Management in Actor Systems for Cloud-Native Applications

IncBoost: Scaling Incremental Graph Processing for Edge Deletions and Weight Updates

Memory Management in Complex Join Queries: A Re-evaluation Study

FAAStloop: Optimizing Loop-Based Applications for Serverless Computing

Distributed Training of Large Language Models on AWS Trainium

Near-Lossless Gradient Compression for Data-Parallel Distributed DNN Training

Accelerating Transfer Learning with Near-Data Computation on Cloud Object Stores

Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization

ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks