← Back to home

Publications

* indicates the corresponding author; # indicates co-first authors.

2026

  1. [EMNLP 2026]
    GROVE: Graph-based Routing Over Variant Experts for Adaptive Two-Stage Training of Reasoning Models.
    Yiming Luo, Chunlin Tian*, and Li Li
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP’26), Oct 2026
  2. [MICCAI 2026]
    SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space.
    Huanrong Liu#, Chunlin Tian#, Tongyu Jia, Tailai Zhou, Qin Liu, Yu Gao, Yutong Ban, Yun Gu, Guy Rosman, Xin Ma, and Qingbiao Li
    In Proceedings of the 29th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI’26), 2026
  3. [TPDS 2026]
    Floe: Federated Specialization for Real-Time LLM-SLM Inference.
    Chunlin Tian, Kahou Tam, Yebo Wu, Shuaihang Zhong, Li Li, Nicholas D. Lane, and Chengzhong Xu
    IEEE Transactions on Parallel and Distributed Systems (TPDS), Jul 2026
  4. [ACL 2026]🏆 Oral Presentation
    Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge.
    Yebo Wu, Jingguang Li, Chunlin Tian, KaHou Tam, Zhijiang Guo, and Li Li
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL’26), Jul 2026
  5. [SoCC 2026]
    Memory-Decoupled Layer-Wise Fine-Tuning for Efficient On-Device LLM Adaptation.
    Yebo Wu, Jingguang Li, Chunlin Tian, Kahou Tam, Zhijiang Guo, and Li Li
    In Proceedings of the 2026 ACM Symposium on Cloud Computing (SoCC’26), Nov 2026
  6. [TPDS 2026]
    Transcending Memory Constraints in Federated Learning via Sequential Block-Wise Training.
    Yebo Wu, Chunlin Tian, Kahou Tam, Zichen Xu, Xiaobo Zhou, and Li Li*
    IEEE Transactions on Parallel and Distributed Systems (TPDS), 2026
  7. [TMLR 2026]
    A Survey on Federated Fine-Tuning of Large Language Models.
    Yebo Wu, Chunlin Tian, Jingguang Li, He Sun, KaHou Tam, Zhanting Zhou, Haicheng Liao, Jing Xiong, Zhijiang Guo, Li Li, and Chengzhong Xu
    Transactions on Machine Learning Research (TMLR), 2026

2025

  1. [USENIX ATC 2025]🏆 Highest-cited paper at USENIX ATC 2025 (1/100)
    CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge.
    Chunlin Tian, Xinpeng Qin, Kahou Tam, Li Li, Zijian Wang, Yuanzhe Zhao, Minglei Zhang, and Chengzhong Xu
    In Proceedings of the 2025 USENIX Annual Technical Conference (USENIX ATC’25), Jul 2025
  2. [CICC 2025]
    A One-Shot Floating-Point Compute-in-Memory Macro Featuring PVT Robustness and Mismatch Tolerance for Edge LLMs.
    Yuanzhe Zhao, Heng Xie, Zijian Wang, Chunlin Tian, Li Li, Yan Zhu, Rui Paulo Martins, Chi-Hang Chan, and Minglei Zhang
    In Proceedings of the IEEE Custom Integrated Circuits Conference (CICC’25), Apr 2025
  3. [ICLR 2025 SCOPE Workshop]
    AsymLoRA: Harmonizing Data Conflicts and Commonalities in MLLMs.
    Xuyang Wei, Chunlin Tian, and Li Li
    In Proceedings of the SCOPE Workshop at ICLR 2025, Apr 2025

2024

  1. [NeurIPS 2024]🏆 Oral Presentation (Top 0.4%)
    HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning.
    Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, and Chengzhong Xu
    In Advances in Neural Information Processing Systems 37 (NeurIPS’24), Dec 2024
  2. [ICML 2024]
    Ranking-based Client Imitation Selection for Efficient Federated Learning.
    Chunlin Tian, Zhan Shi, Xinpeng Qin, Li Li, and Chengzhong Xu
    In Proceedings of the Forty-First International Conference on Machine Learning (ICML’24), Jul 2024
  3. [TPDS 2024]
    Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting.
    Chunlin Tian, Li Li, Kahou Tam, Yebo Wu, and Chengzhong Xu
    IEEE Transactions on Parallel and Distributed Systems (TPDS), Dec 2024
  4. [SenSys 2024]
    FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management.
    Kahou Tam, Chunlin Tian, Li Li, Haikai Zhao, and Chengzhong Xu
    In Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems (SenSys’24), Nov 2024
  5. [IJCAI 2024]
    FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization.
    Zhiyuan Ning#, Chunlin Tian#, Meng Xiao, Wei Fan, Pengyang Wang, Li Li, Pengfei Wang, and Yuanchun Zhou
    In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI’24), Aug 2024
  6. [IWQoS 2024]
    GreenLLM: Towards Efficient Large Language Model via Energy-aware Pruning.
    Chunlin Tian, Xinpeng Qin, and Li Li
    In Proceedings of the IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS’24), Jun 2024
  7. [IWQoS 2024]
    Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing.
    Yebo Wu, Li Li, Chunlin Tian, Chang Tao, Chi Lin, Cong Wang, and Chengzhong Xu
    In Proceedings of the IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS’24), Jun 2024
  8. [IWQoS 2024]
    Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained Blocks.
    Shichen Zhan, Yebo Wu, Chunlin Tian, Yan Zhao, and Li Li
    In Proceedings of the IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS’24), Jun 2024
  9. [IWQoS 2024]
    FedMG: A Federated Multi-Global Optimization Framework for Autonomous Driving Control.
    Jialiang Ma, Chunlin Tian, Li Li, and Chengzhong Xu
    In Proceedings of the IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS’24), Jun 2024
  10. [ACM MM 2024]🏆 Oral Presentation (Top 4%)
    When, Where, and What? A Benchmark for Accident Anticipation and Localization with Large Language Models.
    Haicheng Liao, Yongkang Li, Chengyue Wang, Yanchen Guan, Kahou Tam, Chunlin Tian, Li Li, Chengzhong Xu, and Zhenning Li
    In Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM’24), Oct 2024
  11. [ACM MM 2024]
    CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions.
    Haicheng Liao, Haoyu Sun, Huanming Shen, Chengyue Wang, Kahou Tam, Chunlin Tian, Li Li, Chengzhong Xu, and Zhenning Li
    In Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM’24), Oct 2024
  12. [ECAI 2024]
    Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction.
    Haicheng Liao, Yongkang Li, Zhenning Li, Chengyue Wang, Guofa Li, Chunlin Tian, Zilin Bian, Kaiqun Zhu, Zhiyong Cui, and Jia Hu
    In Proceedings of the 27th European Conference on Artificial Intelligence (ECAI’24), Oct 2024

2023

  1. [ICLR 2023 Tiny Papers]
    Learn to Select: Efficient Cross-device Federated Learning via Reinforcement Learning.
    Chunlin Tian, Zhan Shi, and Li Li
    In Proceedings of the ICLR 2023 Tiny Papers Track, May 2023
  2. [IJCAI 2023 GLOW Workshop]
    Breaking On-device Training Memory Wall: A Systematic Survey.
    Shitian Li, Chunlin Tian*, Kahou Tam, Rui Ma, and Li Li
    In Proceedings of the GLOW Workshop at IJCAI 2023, Aug 2023

2022

  1. [MICRO 2022]
    HARMONY: Heterogeneity-Aware Hierarchical Management for Federated Learning System.
    Chunlin Tian, Li Li, Zhan Shi, Jun Wang, and Chengzhong Xu
    In Proceedings of the 55th IEEE/ACM International Symposium on Microarchitecture (MICRO’22), Oct 2022