Erhu Feng

Orcid: 0009-0006-5957-3024

According to our database1, Erhu Feng authored at least 18 papers between 2021 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
MobiFlow: Real-World Mobile Agent Benchmarking through Trajectory Fusion.
CoRR, April, 2026

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses.
CoRR, April, 2026

History Doesn't Repeat Itself but Rollouts Rhyme: Accelerating Reinforcement Learning with RhymeRL.
Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2026

2025
Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM.
CoRR, December, 2025

From Principles to Practice: A Systematic Study of LLM Serving on Multi-core NPUs.
CoRR, October, 2025

MobiAgent: A Systematic Framework for Customizable Mobile Agents.
CoRR, September, 2025

History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL.
CoRR, August, 2025

Leveraging OS-Level Primitives for Robotic Action Management.
CoRR, August, 2025

Get Experience from Practice: LLM Agents with Record & Replay.
CoRR, May, 2025

HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs platform with Heterogeneous AI Accelerators.
CoRR, January, 2025

Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference.
Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles, 2025

Topology-Aware Virtualization over Inter-Core Connected Neural Processing Units.
Proceedings of the 52nd Annual International Symposium on Computer Architecture, 2025

2024
sNPU: Trusted Execution Environments on Integrated NPUs.
Proceedings of the 51st ACM/IEEE Annual International Symposium on Computer Architecture, 2024

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing.
Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2024

sIOPMP: Scalable and Efficient I/O Protection for TEEs.
Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2024

2023
Efficient Distributed Secure Memory with Migratable Merkle Tree.
Proceedings of the IEEE International Symposium on High-Performance Computer Architecture, 2023

2022
Towards A Secure Joint Cloud With Confidential Computing.
Proceedings of the IEEE International Conference on Joint Cloud Computing, 2022

2021
Scalable Memory Protection in the PENGLAI Enclave.
Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation, 2021


  Loading...