Xinming Wei

Publications

Grouped by year. See also my Google Scholar profile.

2026

  1. UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

    Xinming Wei, Chao Jin, Tuo Dai, Yinmin Zhong, Shan Yu, Chengxu Yang, Bingyang Wu, Zili Zhang, Jing Mai, Qianchao Zhu, Zhouyang Li, Yuliang Liu, Guojie Luo

    Preprint

  2. ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning

    Chao Jin, Xinming Wei, Yinmin Zhong, C. Yang, B. Wu, R. Zhu, Z. Zhang, Yuliang Liu, Xin Jin

    Preprint

  3. ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels

    Bingyang Wu, Chao Jin, Zili Zhang, Xinming Wei, Y. Zhong, R. Zhu, C. Yang, Xin Jin, Yuliang Liu

    Preprint

  4. Heddle: A Distributed Orchestration System for Agentic RL Rollout

    Zili Zhang, Yinmin Zhong, Chengxu Yang, Chao Jin, Bingyang Wu, Xinming Wei, Yuliang Liu, Xin Jin

    Preprint

2025

  1. Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC

    Xinming Wei, Jiahao Zhang, Haoran Li, J. Chen, H. Guan, R. Qu, M. Li, X. Chen, Guojie Luo

    Preprint

  2. TACPlace: Ultrafast Thermal-Aware Chiplet Placement with Feasibility Seeking

    Shan Yu*, Haiyang Liu*, Xinming Wei*, Bizhao Shi, Guojie Luo (*Equal contribution)

    Great Lakes Symposium on VLSI (GLSVLSI)

2024

  1. AceRoute: Adaptive Compute-Efficient FPGA Routing with Pluggable Intra-Connection Bidirectional Exploration

    Xinming Wei, Ziyun Zhang, Sunan Zou, Kaiwen Sun, Jiahao Zhang, Jiaxi Zhang, Ping Fan, Guojie Luo

    IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

  2. Rethinking IC Layout Vulnerability: Simulation-Based Hardware Trojan Threat Assessment with High Fidelity

    Xinming Wei, Jiaxi Zhang, Guojie Luo

    IEEE Symposium on Security and Privacy (S&P)

  3. Autoformalizing Mathematical Statements by Symbolic Equivalence and Semantic Consistency

    Zenan Li, Yifan Wu, Zhaoyu Li, Xinming Wei, Xian Zhang, Fan Yang, Xiaoxing Ma

    Conference on Neural Information Processing Systems (NeurIPS)

2023

  1. GDSII-Guard: ECO Anti-Trojan Optimization with Exploratory Timing-Security Trade-Offs

    Xinming Wei, Jiaxi Zhang, Guojie Luo

    ACM/IEEE Design Automation Conference (DAC)

2022

  1. Purlin: A Versatile Toolkit for the Generation and Simulation of On-Chip Network

    Yijiang Guo, Xinming Wei, Jiaxi Zhang, Guojie Luo

    IEEE International Conference on Computer Design (ICCD)