Weilin Cai

21 papers A* 3C 2Journal 11Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Automated emotional design generation for NEV wheel hubs: Integrating StyleGAN2-ADA and WOA-SVR within Kansei engineering.
Expert Syst. Appl.
Yi Wang, Meiyu Zhou, Zhengyu Wang, Weilin Cai, Xin Sun, Huijuan Zhu
2025 J jnl
A Survey on Mixture of Experts in Large Language Models.
IEEE Trans. Knowl. Data Eng.
Weilin Cai, Juyong Jiang, Fan Wang, Jing Tang, Sunghun Kim, Jiayi Huang
2025 J jnl
Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding.
CoRR
Zhibin Wang, Zhonghui Zhang, Yuhang Zhou, Zibo Wang, Mo Zhou, Peng Jiang, Weilin Cai, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian
2025 — conf
Action-Priority Driven Policy Optimization for Flexible Job Shop Scheduling Problem.
CDC
Wenjun Zheng, Weilin Cai, Wei Qu, Jianfeng Mao
2025 — conf
Aesthetic and Emotional Preferences in Wheel Hub Design for New Energy Vehicles.
HCI (84)
Yi Wang, Meiyu Zhou, Weilin Cai, Zhengyu Wang
2025 J jnl
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts.
CoRR
Shwai He, Weilin Cai, Jiayi Huang, Ang Li
2025 A* conf
Chimera: Communication Fusion for Hybrid Parallelism in Large Language Models.
ISCA
Le Qin, Junwei Cui, Weilin Cai, Jiayi Huang
2025 J jnl
DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction.
CoRR
Weilin Cai, Le Qin, Shwai He, Junwei Cui, Ang Li, Jiayi Huang
2025 — conf
Extended Invalid Action Mask: Training-Time Size-Agnostic Safe Reinforcement Learning for Flexible Job Shop Scheduling Problems.
CASE
Weilin Cai, Wenjun Zheng, Zhaoli Wang, Yilan Chen, Jianfeng Mao
2025 — conf
MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training.
ASPLOS (2)
Weilin Cai, Le Qin, Jiayi Huang
2025 A* conf
Optimizing All-to-All Collective Communication with Fault Tolerance on Torus Networks.
MICRO
Le Qin, Junwei Cui, Weilin Cai, Meng Niu, Yan Yang, Jiayi Huang
2025 A* conf
Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts.
ICML
Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, Jiayi Huang
2025 — conf
Wheelchair Form Design Method Based on Grey Relational Analysis and Quantitative Theory Type I.
HCI (83)
Weilin Cai, Meiyu Zhou, Yi Wang, Zhengyu Wang
2024 J jnl
A Survey on Mixture of Experts.
CoRR
Weilin Cai, Juyong Jiang, Fan Wang, Jing Tang, Sunghun Kim, Jiayi Huang
2024 J jnl
Partial Experts Checkpoint: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training.
CoRR
Weilin Cai, Le Qin, Jiayi Huang
2024 J jnl
Reinforcement-Learning-Informed Prescriptive Analytics for Air Traffic Flow Management.
IEEE Trans Autom. Sci. Eng.
Yuan Wang, Weilin Cai, Yilei Tu, Jianfeng Mao
2024 J jnl
Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts.
CoRR
Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, Jiayi Huang
2022 J jnl
Extending τ-Lop to model MPI blocking primitives on shared memory.
J. Supercomput.
Ziheng Wang, Heng Chen, Xiaoshe Dong, Weilin Cai, Yan Kang, Xingjun Zhang
2022 C conf
Flexible Supervision System: A Fast Fault-Tolerance Strategy for Cloud Applications in Cloud-Edge Collaborative Environments.
NPC
Weilin Cai, Heng Chen, Zhimin Zhuo, Ziheng Wang, Ninggang An
2022 J jnl
Implementation and optimization of ChaCha20 stream cipher on sunway taihuLight supercomputer.
J. Supercomput.
Weilin Cai, Heng Chen, Ziheng Wang, Xingjun Zhang
2019 C conf
An Exploratory Study on Judicial Image Quality Assessment Based on Deep Learning.
QRS
Qiqi Gu, Weilin Cai, Shengcheng Yu, Zhenyu Chen