|
[EuroSys'25]
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
|
Week 2 |
|
钟睿熙 |
|
[SIGCOMM'24]
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
|
Week 3 |
|
付仕豪 |
|
[SIGCOMM'25]
MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism
|
Week 3 |
|
周正华 |
|
[MobiSys'26]
TimelyLLM: Time-sensitive LLM Serving System for Physical-I/O Limited Agents
|
Week 4 |
|
张睿恺 |
|
[SIGCOMM'24]
Alibaba HPN: A Data Center Network for Large Language Model Training
|
Week 4 |
|
李梓璇 |
|
[MobiSys'26]
SAIL: Redesigning Collaborative Language Inference with a Single Server-to-Mobile Handoff
|
Week 5 |
|
丁紫璇 |
|
[SIGCOMM'25]
ResCCL: Resource-Efficient Scheduling for Collective Communication
|
Week 5 |
|
蔡婷 |
|
[OSDI'26]
UCCL-Tran: An Extensible Software Transport Layer for GPU Networking
|
Week 6 |
|
王宇 |
|
[SIGCOMM'25]
MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training
|
Week 6 |
|
武珂晗 |
|
[SIGCOMM'25]
ByteScale: Communication-Efficient Scaling of LLM Training with a 2048K Context Length on 16384 GPUs
|
Week 7 |
|
庞韵 |
|
[ASPLOS'24]
TCCL: Discovering Better Communication Paths for PCIe GPU Clusters
|
Week 7 |
|
窦正 |
|
[SIGCOMM'24]
m3: Accurate Flow-Level Performance Estimation using Machine Learning
|
Week 8 |
|
丁晓琪 |
|
[SIGCOMM'25]
Towards LLM-Based Failure Localization in Production-Scale Networks
|
Week 8 |
|
黄馨卉 |
|
[SIGCOMM'24]
Transferable Neural WAN TE for Changing Topologies
|
Week 9 |
|
李渤 |
|
[SIGCOMM'26]
AIDA: Accelerating Root Cause Analysis for Multi-Vendor Device Failures with LLM-Powered Reasoning
|
Week 9 |
|
李俊艺 |
|
[SIGCOMM'25]
Hattrick: Solving Multi-Class TE using Neural Models
|
Week 10 |
|
孙泳 |
|
[SIGCOMM'25]
StarCDN: Moving Content Delivery Networks to Space
|
Week 10 |
|
姚凯文 |
|
[SIGCOMM'25]
Direct-to-Cell Satellite Network without Satellite Navigation
|
Week 11 |
|
田鹏宇 |
|
[ASPLOS'25]
Earth+: On-Board Satellite Imagery Compression Leveraging Historical Earth Observations
|
Week 11 |
|
郑好 |
|
[SIGCOMM'25]
DeepSpace: Super Resolution Powered Efficient and Reliable Satellite Image Data Acquistion
|
Week 12 |
|
陈曦 |
|
[SIGCOMM'24]
Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and Prediction
|
Week 12 |
|
张妞妞 |
|
[MobiCom'25]
How to Update Your 5G vRAN
|
Week 13 |
|
吕翰琪 |
|
[SIGCOMM'24]
Unveiling the 5G Mid-Band Landscape: From Network Deployment to Performance and Application QoE
|
Week 13 |
|
吴宇捷 |
|
[MobiSys'24]
ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling
|
Week 14 |
|
刘浩 |
|
[MobiSys'24]
CoActo: CoActive Neural Network Inference Offloading with Fine-grained and Concurrent Execution
|
Week 14 |
|
雷正华 |
|
[MobiSys'25]
EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices
|
Week 15 |
|
黄昊 |
|
[EuroSys'24]
Totoro: A Scalable Federated Learning Engine for the Edge
|
Week 15 |
|
韩睿勍 |
|
[MobiSys'24]
NeRFHub: A Context-Aware NeRF Serving Framework for Mobile Immersive Applications
|
Week 16 |
|
李冬阳 |
|
[MobiSys'26]
A Greener Edge: A Framework on Carbon-aware Edge ML System Design
|
Week 16 |
|
陈晟 |