Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Wangsong Yin
Observed names:
YIN, Wangsong,
Yin, Wangsong
Institution:
Peking University
Observed institutions:
Beijing University of Posts and Telecommunications,
Peking University,
State Key Laboratory of Networking and Switching Technology,
Tsinghua University
ORCID:
0009-0000-6242-4368
Observed ORCID:
0009-0000-6242-4368
OpenAlex ID:
A5101293258
EdgeLLM: Fast On-Device LLM Inference With Speculative Decoding
2024
·
Daliang Xu
, Wangsong Yin
, et al.
·
IEEE Transactions on Mobile Computing
·
50
Resource-efficient Algorithms and Systems of Foundation Models: A Survey
2024
·
Mengwei Xu
, Dongqi Cai
, et al.
·
ACM Computing Surveys
·
44
A Survey of Resource-efficient LLM and Multimodal Foundation Models
2024
·
Xu, Mengwei
, Yin, Wangsong
, et al.
·
arXiv (Cornell University)
·
44
PDF
LLMCad: Fast and Scalable On-device Large Language Model Inference
2023
·
Xu, Daliang
, Yin, Wangsong
, et al.
·
arXiv (Cornell University)
·
16
PDF
LLM as a System Service on Mobile Devices
2024
·
Yin, Wangsong
, Xu, Mengwei
, et al.
·
arXiv (Cornell University)
·
10
PDF
Elastic On-Device LLM Service
2025
·
Wangsong Yin
, Rongjie Yi
, et al.
·
ACM Annual International Conference on Mobile Computing and Networking (MobiCom)
·
5
PDF
PieBridge: Fast and Parameter-Efficient On-Device Training via Proxy Networks
2024
·
Wangsong Yin
, Daliang Xu
, et al.
·
ACM Conference on Embedded Networked Sensor Systems (SenSys)
·
1
PDF
EdgeCraft: Automated Model Crafting for Edge IoT
2026
·
Wang, Genglin
, Liu, Kaiwei
, et al.
·
arXiv (Cornell University)
PDF
CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion
2026
·
Wang, Genglin
, Yin, Wangsong
, et al.
·
arXiv (Cornell University)
PDF
OmniTide: Co-Designing Algorithms and Systems for Efficient On-Device Omni-LLM Streaming
2026
·
Shen, Zongshang
, Yin, Wangsong
, et al.
·
arXiv (Cornell University)
PDF
Empowering Hybrid Attention Models on NPUs
2026
·
Zhang, Yinyuan
, Xu, Daliang
, et al.
·
arXiv (Cornell University)
PDF
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
2026
·
Wangsong Yin
, Daliang Xu
, et al.
·
International Conference on Mobile Systems, Applications, and Services
An Efficient Context Management System for On-Device LLMaaS
2026
·
Wangsong Yin
, Mengwei Xu
, et al.
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
2026
·
YIN, Wangsong
·
Zenodo (CERN European Organization for Nuclear Research)
Show more works
View as search
Works count:
15
Citation count:
170
H-index:
5
I10-index:
5
Year
Topic
Type
