Xiaoniu Song

Orcid: 0009-0009-1887-2636

According to our database1, Xiaoniu Song authored at least 6 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Unified and Near-optimal Multi-GPU Cache for Embedding-based Deep Learning.
ACM Trans. Comput. Syst., February, 2026

2025
StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation.
CoRR, April, 2025

Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model.
CoRR, March, 2025

2024
ProMoE: Fast MoE-based LLM Serving using Proactive Caching.
CoRR, 2024

2023
UGACHE: A Unified GPU Cache for Embedding-based Deep Learning.
Proceedings of the 29th Symposium on Operating Systems Principles, 2023

2022
GNNLab: a factored system for sample-based GNN training over GPUs.
Proceedings of the EuroSys '22: Seventeenth European Conference on Computer Systems, Rennes, France, April 5, 2022


  Loading...