ACM SIGCOMM 2026 Regional Pods - Thailand
Venues:
- Bangkok: Room 301, Office of Computer Services building, Kasetsart University, Bangkok, Thailand
- Khon Kaen: Room SC9428, College of Computing, Khon Kaen University, Khon Kaen, Thailand
Local Time Zone: UTC+7
| 20 August 2026 | |
|---|---|
| 09:00 - 10:15 | Recorded SIGCOMM presentations
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
Elastispec: Formalizing Enterprise Firewall Management with Informal and Elastic Specifications
DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce
Turbo: Efficiently Serving Long-Context Large Language Models with In-Network Aggregation |
| 10:15 - 10:25 | Morning Break 1 |
| 10:25 - 12:00 | Recorded SIGCOMM presentations
Anytest: Localizing the Root Cause of Hardware Transport Performance Anomalies
PReCCL: Performant and Resilient Collective Communication via Integrated Inband Telemetry and Workload Reallocation
RANPilot: Making AI Functionalities Robust to Dynamic O-RAN Reconfigurations
SAGE: A Real-Time AI System for Reducing Latency in NextG Cellular Networks
LITE: Loss-resilient Immersive Telepresence with Multi-modal Semantics |
| 12:05 - 13:00 | Lunch |
| 13:00 - 14:35 | Recorded SIGCOMM presentations
Pegasus: A Data Center Network for Bare-Metal AI Cloud
Concord: Airtime-Aware Contention Control for Taming Tail Latency from Wi-Fi Frame Bursting
CausalTune: Causal Learning based Automated Cellular RAN Configuration Tuning Framework
DistDPU: A Disaggregated DPU Architecture for High-Performance and Cost-Efficient AI Clouds |
| 14:35 - 14:45 | Afternoon Break 1 |
| 14:45 - 16:20 | Recorded SIGCOMM presentations
Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks
OptCCL: Scalable Synthesis of Optimal Collective Communication Algorithms
Theseus: Runtime-Adaptive GPU Collective Communication with Hot-Swappable Schedules
Unveiling Low-Altitude 5G Performance: Linking Key Influencing Factors with UAV Flight Parameters |
| 21 August 2026 | |
| 09:00 - 10:00 | Live Q&A Session 1. SAGE: A Real-Time AI System for Reducing Latency in NextG Cellular Networks 2. Near-optimal Online Traffic Engineering 3. Pegasus: A Data Center Network for Bare-Metal AI Cloud 4. RANPilot: Making AI Functionalities Robust to Dynamic O-RAN Reconfigurations 5. Tuning into the Web: A Low-Cost Access Solution for Developing Countries *This is subjected to change |
| 10:00 - 10:25 | Morning Break 1 |
| 10:25 - 12:00 | Recorded SIGCOMM presentations
A Global Inference and Assessment of Large Shared IP Addresses
Zero-Knowledge Cloud Analytics
Tuning into the Web: A Low-Cost Access Solution for Developing Countries
Near-optimal Online Traffic Engineering |
| 12:05 - 13:00 | Lunch |
| 13:00 - 14:35 | Recorded SIGCOMM presentations
Honey, I Shrunk the Headers With Flow.ZIP
DeepSFU: Scalable Deepfake Detection for Video Conferencing
Contiguous Zero-Copy for Encrypted Transport Protocols
CSIG: Congestion Signaling for Datacenter Transports |
| 14:35 - 14:45 | Afternoon Break 1 |
| 14:45 - 16:20 | Recorded SIGCOMM presentations
Towards High-Performance Intrusion Detection with Robustness Guarantees on Programmable Switches at ISP Scale
λλ: A Programming Language for Silicon Photonics
Understanding Host Network Stack Latency
STORM: Enabling Traffic Scheduling for RDMA
Opus: Photonic Rail-Optimized Fabric in ML Datacenters |