@unpublished{63530,
  abstract     = {{The widespread deployment of 5G networks, together with the coexistence of 4G/LTE networks, provides mobile devices a diverse set of candidate cells to connect to. However, associating mobile devices to cells to maximize overall network performance, a.k.a. cell (re)selection, remains a key challenge for mobile operators. Today, cell (re)selection parameters are typically configured manually based on operator experience and rarely adapted to dynamic network conditions. In this work, we ask: Can an agent automatically learn and adapt cell (re)selection parameters to consistently improve network performance? We present a reinforcement learning (RL)-based framework called CellPilot that adaptively tunes cell (re)selection parameters by learning spatiotemporal patterns of mobile network dynamics. Our study with real-world data demonstrates that even a lightweight RL agent can outperform conventional heuristic reconfigurations by up to 167%, while generalizing effectively across different network scenarios. These results indicate that data-driven approaches can significantly improve cell (re)selection configurations and enhance mobile network performance.}},
  author       = {{Illian, Marvin and Khalili, Ramin and Rocha, Antonio A. de A. and Wang, Lin}},
  booktitle    = {{arXiv:2601.04083}},
  title        = {{{Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}}},
  year         = {{2026}},
}

@inproceedings{65249,
  author       = {{Shaaban KabakiboKabakibo, Huzaifa and Trivedi, Animesh and Wang, Lin}},
  booktitle    = {{The 9th Annual Conference on Machine Learning and Systems (MLSys)}},
  location     = {{Bellevue, WA}},
  title        = {{{Breaking the Ice: Analyzing Cold Start Latency in vLLM}}},
  year         = {{2026}},
}

@inproceedings{65250,
  author       = {{Zohdi, Sepideh and Wang, Lin}},
  booktitle    = {{The 6th Workshop on Machine Learning and Systems (EuroMLSys)}},
  location     = {{Edinburg}},
  title        = {{{Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models }}},
  year         = {{2026}},
}

@inproceedings{65013,
  author       = {{Illian, Marvin and Khalili, Ramin and A. de A. Rocha, Antonio and Wang, Lin}},
  booktitle    = {{2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)}},
  publisher    = {{IFIP}},
  title        = {{{Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}}},
  year         = {{2026}},
}

@inproceedings{63054,
  author       = {{Apostolo, Guilherme Henrique and Bauszat, Pablo and Nigade, Vinod and Bal, Henri E. and Wang, Lin}},
  booktitle    = {{Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)}},
  location     = {{Hong Kong, China}},
  publisher    = {{ACM}},
  title        = {{{Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices}}},
  doi          = {{10.1145/3680207.3765260}},
  year         = {{2025}},
}

@article{63057,
  author       = {{Pei, Qiangyu and Yuan, Yongjie and Hu, Haichuan and Wang, Lin and Zhang, Dong and Yan, Bingheng and Yu, Chen and Liu, Fangming}},
  issn         = {{2377-3782}},
  journal      = {{IEEE Transactions on Sustainable Computing}},
  number       = {{4}},
  pages        = {{804--819}},
  publisher    = {{Institute of Electrical and Electronics Engineers (IEEE)}},
  title        = {{{Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters}}},
  doi          = {{10.1109/tsusc.2025.3542563}},
  volume       = {{10}},
  year         = {{2025}},
}

@inproceedings{63056,
  author       = {{Wu, Jing and Wang, Lin and Deng, Quanfeng and Yu, Chen and Zhang, Dong and Yan, Bingheng and Liu, Fangming}},
  booktitle    = {{2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}},
  location     = {{Milan, Italy}},
  publisher    = {{IEEE}},
  title        = {{{It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation}}},
  doi          = {{10.1109/ipdps64566.2025.00012}},
  year         = {{2025}},
}

@inproceedings{61256,
  author       = {{Illian, Marvin and Luchterhandt, Björn and Wang, Lin}},
  booktitle    = {{Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)}},
  location     = {{Hong Kong, China}},
  title        = {{{Band Switching for Mobile Energy Optimization in 5G Networks and Beyond}}},
  doi          = {{10.1145/3737897.3767294}},
  year         = {{2025}},
}

@inproceedings{63058,
  author       = {{Ghafouri, Saeid and Razavi, Kamran and Salmani, Mehran and Sanaee, Alireza and Botran, Tania Lorido and Wang, Lin and Doyle, Joseph and Jamshidi, Pooyan}},
  booktitle    = {{Companion of the 16th ACM/SPEC International Conference on Performance Engineering}},
  publisher    = {{ACM}},
  title        = {{{IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency}}},
  doi          = {{10.1145/3680256.3721266}},
  year         = {{2025}},
}

@inproceedings{50807,
  author       = {{Hu, Haichuan and Liu, Fangming and Pei, Qiangyu and Yuan, Yongjie and Xu, Zichen and Wang, Lin}},
  booktitle    = {{Proceedings of the ACM Web Conference (WWW)}},
  location     = {{Singapore}},
  publisher    = {{ACM}},
  title        = {{{𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing}}},
  doi          = {{10.1145/3589334.3645383}},
  year         = {{2024}},
}

@article{53531,
  author       = {{Ghafouri, Saeid and Razavi, Kamran and Salmani, Mehran and Sanaee, Alireza and Lorido Botran, Tania  and Wang, Lin and Doyle, Joseph and Jamshidi, Pooyan}},
  journal      = {{Journal of Systems Research (JSys)}},
  title        = {{{IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency}}},
  year         = {{2024}},
}

@inproceedings{55365,
  author       = {{Razavi, Kamran and Davari Fard, Shayan and Karlos, George and Nigade, Vinod and Mühlhäuser, Max and Wang, Lin}},
  booktitle    = {{Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)}},
  location     = {{Paris, France}},
  title        = {{{NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award)}}},
  year         = {{2024}},
}

@inproceedings{53095,
  author       = {{Razavi, Kamran and Ghafouri, Saeid and Mühlhäuser, Max and Jamshidi, Pooyan and Wang, Lin}},
  booktitle    = {{Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024}},
  location     = {{Athens, Greece}},
  publisher    = {{ACM}},
  title        = {{{Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling}}},
  doi          = {{10.1145/3642970.365583}},
  year         = {{2024}},
}

@inproceedings{50066,
  author       = {{Dou, Feng and Wang, Lin and Chen, Shutong and Liu, Fangming}},
  booktitle    = {{Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}},
  location     = {{Vancouver, Canada}},
  publisher    = {{IEEE}},
  title        = {{{X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics}}},
  doi          = {{10.1109/INFOCOM52122.2024.10621341}},
  year         = {{2024}},
}

@inproceedings{53807,
  author       = {{Liu, Gaosheng and Nigade, Vinod and Bal, Henri and Wang, Lin}},
  booktitle    = {{Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)}},
  location     = {{Sydney, Austrialia}},
  title        = {{{A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT}}},
  doi          = {{10.1145/3663408.3663414}},
  year         = {{2024}},
}

@inproceedings{55366,
  author       = {{Karlos, George and Bal, Henri and Wang, Lin}},
  booktitle    = {{Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)}},
  location     = {{Atlanta, GA}},
  title        = {{{NetCL: A Unified Programming Framework for In-Network Computing}}},
  year         = {{2024}},
}

@article{55364,
  author       = {{Liu, Gaosheng and Wang, Lin}},
  journal      = {{IEEE Transactions on Mobile Computing (TMC)}},
  title        = {{{Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing}}},
  doi          = {{10.1109/TMC.2024.3429636}},
  year         = {{2024}},
}

@inproceedings{50065,
  author       = {{Blöcher, Marcel and Nedderhut, Nils and Chuprikov, Pavel and Khalili, Ramin and Eugster, Patrick and Wang, Lin}},
  booktitle    = {{Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}},
  location     = {{Vancouver, Canada}},
  publisher    = {{IEEE}},
  title        = {{{Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES}}},
  doi          = {{10.1109/INFOCOM52122.2024.10621125}},
  year         = {{2024}},
}

@inproceedings{56689,
  author       = {{Pei, Qiangyu and Wang, Lin and Zhang, Dong and Yan, Bingheng and Yu, Chen and Liu, Fangming}},
  booktitle    = {{Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)}},
  location     = {{Redmond}},
  title        = {{{InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment}}},
  year         = {{2024}},
}

@article{63059,
  abstract     = {{<jats:title>Abstract</jats:title><jats:p>While high accuracy is of paramount importance for deep learning (DL) inference, serving inference requests on time is equally critical but has not been carefully studied especially when the request has to be served over a dynamic wireless network at the edge. In this paper, we propose Jellyfish—a novel edge DL inference serving system that achieves soft guarantees for end-to-end inference latency service-level objectives (SLO). Jellyfish handles the network variability by utilizing both data and deep neural network (DNN) adaptation to conduct tradeoffs between accuracy and latency. Jellyfish features a new design that enables collective adaptation policies where the decisions for data and DNN adaptations are aligned and coordinated among multiple users with varying network conditions. We propose efficient algorithms to continuously map users and adapt DNNs at runtime, so that we fulfill latency SLOs while maximizing the overall inference accuracy. We further investigate <jats:italic>dynamic</jats:italic> DNNs, i.e., DNNs that encompass multiple architecture variants, and demonstrate their potential benefit through preliminary experiments. Our experiments based on a prototype implementation and real-world WiFi and LTE network traces show that Jellyfish can meet latency SLOs at around the 99th percentile while maintaining high accuracy.
</jats:p>}},
  author       = {{Nigade, Vinod and Bauszat, Pablo and Bal, Henri and Wang, Lin}},
  issn         = {{0922-6443}},
  journal      = {{Real-Time Systems}},
  number       = {{2}},
  pages        = {{239--290}},
  publisher    = {{Springer Science and Business Media LLC}},
  title        = {{{Inference serving with end-to-end latency SLOs over dynamic edge networks}}},
  doi          = {{10.1007/s11241-024-09418-4}},
  volume       = {{60}},
  year         = {{2024}},
}