Demo Data from EDBT 2026 / reviewers in the wild / expert
Jianzhe Xiao
dblp:405/1227
· DBLP profile ↗
1ranked-venue papers
0as first author
1since 2021 · last 2025
—ORCID · unresolved
Domains — the database's venue-derived domains; a paper can count in several
Computer networks · 1 · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Efficient and distributed learning · 44% Deep learning architectures and training · 44% Language models and text generation · 13% | |
| Computer architecture, parallel and distributed computing, and storage systems
1 paper |
Distributed systems · 100% |
Topics — the 4 heaviest of 4, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Efficient and distributed learning
inference serving |
0.9 | 1 | 2025 | MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism · SIGCOMM 2025 |
Machine learning › Deep learning architectures and training › mixture of experts
mixture-of-experts inference |
0.9 | 1 | 2025 | MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism · SIGCOMM 2025 |
Distributed systems › distributed machine learning
expert parallelism |
0.9 | 1 | 2025 | MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism · SIGCOMM 2025 |
Natural language and speech › Language models and text generation
large language model inference |
0.3 | 1 | 2025 | MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert Parallelism · SIGCOMM 2025 |
Methods — techniques the papers use, named apart from their topics
expert parallelism · 1.7disaggregated serving · 1.7
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | MegaScale-Infer: Efficient Mixture-of-Experts Model Serving with Disaggregated Expert ParallelismabstractMixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely activated architecture shifts feed-forward networks (FFNs) from being compute-intensive to memory-intensive during inference, leading to substantially lower GPU utilization and increased operational costs. Ruidong Zhu, Ziheng Jiang, Chao Jin 0007, Cesar A. Stuardo, Huaping Zhou, Jianzhe Xiao, Lingjun Liu, Haibin Lin, Li-Wen Chang, Jianxi Ye, Xuanzhe Liu, Xin Jin 0008, Xin Liu 0086 |
SIGCOMM | 11 |