| 2026 | ASPLOS | ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression. | Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li, Weile Luo, Qiang Wang, Wei Wang, Xiaowen Chu |
| 2026 | INFOCOM | HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap. | Wenxiang Lin, Xinglin Pan, Lin Zhang, Shaohuai Shi, Xuan Wang, Xiaowen Chu |
| 2026 | INFOCOM | Compass: Dissecting Communication and Computation Operators for Efficient LLM Training. | Guangyu Xiang, Lin Zhang, Haoxuan Yu, Xinglin Pan, Shaohuai Shi, Xiaowen Chu |
| 2026 | SIGCOMM | ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training. | Wenxiang Lin, Xinglin Pan, Ruibo Fan, Shaohuai Shi, Xiaowen Chu |
| 2025 | ASPLOS | FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models. | Xinglin Pan, Wenxiang Lin, Lin Zhang, Shaohuai Shi, Zhenheng Tang, Rui Wang, Bo Li, Xiaowen Chu |
| 2025 | EuroPar | ScheInfer: Efficient Inference of Large Language Models with Task Scheduling on Moderate GPUs. | Wenxiang Lin, Xinglin Pan, Shaohuai Shi, Xuan Wang, Xiaowen Chu |
| 2025 | ICDCS | Mast: Efficient Training of Mixture-of-Experts Transformers with Task Pipelining and Ordering. | Wenxiang Lin, Xinglin Pan, Shaohuai Shi, Xuan Wang, Bo Li, Xiaowen Chu |
| 2025 | ICDCS | Mitigating Contention in Stream Multiprocessors for Pipelined Mixture of Experts: An SM-Aware Scheduling Approach. | Xinglin Pan, Rui Wang, Wenxiang Lin, Shaohuai Shi, Xiaowen Chu |
| 2024 | ECCV | Multi-task Domain Adaptation for Language Grounding with 3D Objects. | Penglei Sun, Yaoxian Song, Xinglin Pan, Peijie Dong, Xiaofei Yang, Qiang Wang, Zhixu Li, Tiefeng Li, Xiaowen Chu |
| 2024 | EuroSys | ScheMoE: An Extensible Mixture-of-Experts Distributed Training System with Tasks Scheduling. | Shaohuai Shi, Xinglin Pan, Qiang Wang, Chengjian Liu, Xiaozhe Ren, Zhongzhe Hu, Yu Yang, Bo Li, Xiaowen Chu |
| 2024 | ICML | Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models. | Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Xinglin Pan, Qiang Wang, Xiaowen Chu |
| 2024 | INFOCOM | Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules. | Xinglin Pan, Wenxiang Lin, Shaohuai Shi, Xiaowen Chu, Weinong Sun, Bo Li |
| 2023 | ICONIP | Generalized Category Discovery with Clustering Assignment Consistency. | Xiangli Yang, Xinglin Pan, Irwin King, Zenglin Xu |
| 2023 | INFOCOM | PipeMoE: Accelerating Mixture-of-Experts through Adaptive Pipelining. | Shaohuai Shi, Xinglin Pan, Xiaowen Chu, Bo Li |
| 2022 | ICDCS | ENIGMA: Low-Latency and Privacy-Preserving Edge Inference on Heterogeneous Neural Network Accelerators. | Qiushi Li, Ju Ren, Xinglin Pan, Yuezhi Zhou, Yaoxue Zhang |