Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Chunming Hu

Chunming Hu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Distributed×2AI×2ML×2Performance×2Crypto×1Software Eng.×1

Frequent co-authors

Tianyu Wo2×
Renyu Yang2×
Dihao Fan1×
Jian Zhang1×
Yasai Shi1×
Chuan Luo1×

Research Timeline

2026
CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context support.

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving

This paper presents SpecBox, a runtime system for LLM agents that uses speculative sandbox preallocation to improve resource utilization and reduce interactive tail latency.

Context-Aware Functional Modeling for Android Third-Party Library Detection

This paper proposes LibFan, a learning-based approach to detect third-party libraries in Android apps.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.SEEmpiricalRecentSep 25, 2026

Context-Aware Functional Modeling for Android Third-Party Library Detection

Dihao Fan, Jian Zhang, Yasai Shi, Chuan Luo +4 more

This paper proposes LibFan, a learning-based approach to detect third-party libraries in Android apps.

View →
cs.DCcs.AIcs.LGEmpirical
Recent
Jul 27, 2026

SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving

Yihui Zhang, Tianyu Wo, Jinghao Wang, Xiaoyang Sun +6 more

This paper presents SpecBox, a runtime system for LLM agents that uses speculative sandbox preallocation to improve resource utilization and reduce interactive tail latency.

View →
cs.DCcs.AIcs.LGEmpiricalRecentJun 23, 2026

CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

Zhuoren Ye, Tianyu Wo, Dinghao Xue, Mingming Zhang +3 more

This paper proposes CrossPool, a serving engine for cold Machine Learning Models (LLMs) that separates weights and KV-cache into two GPU memory pools to improve GPU memory utilization and long-context…

View →