[{"year":"2026","citation":{"apa":"Illian, M., Khalili, R., Rocha, A. A. de A., &#38; Wang, L. (2026). Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning. In <i>arXiv:2601.04083</i>.","mla":"Illian, Marvin, et al. “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning.” <i>ArXiv:2601.04083</i>, 2026.","short":"M. Illian, R. Khalili, A.A. de A. Rocha, L. Wang, ArXiv:2601.04083 (2026).","bibtex":"@article{Illian_Khalili_Rocha_Wang_2026, title={Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}, journal={arXiv:2601.04083}, author={Illian, Marvin and Khalili, Ramin and Rocha, Antonio A. de A. and Wang, Lin}, year={2026} }","chicago":"Illian, Marvin, Ramin Khalili, Antonio A. de A. Rocha, and Lin Wang. “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning.” <i>ArXiv:2601.04083</i>, 2026.","ieee":"M. Illian, R. Khalili, A. A. de A. Rocha, and L. Wang, “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning,” <i>arXiv:2601.04083</i>. 2026.","ama":"Illian M, Khalili R, Rocha AA de A, Wang L. Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning. <i>arXiv:260104083</i>. Published online 2026."},"date_updated":"2026-03-31T06:44:22Z","author":[{"first_name":"Marvin","orcid":"0009-0007-2992-8346","last_name":"Illian","full_name":"Illian, Marvin","id":"44169"},{"first_name":"Ramin","full_name":"Khalili, Ramin","last_name":"Khalili"},{"last_name":"Rocha","full_name":"Rocha, Antonio A. de A.","first_name":"Antonio A. de A."},{"last_name":"Wang","orcid":"0000-0001-7181-6128","id":"102868","full_name":"Wang, Lin","first_name":"Lin"}],"date_created":"2026-01-08T07:58:22Z","title":"Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning","publication":"arXiv:2601.04083","type":"preprint","abstract":[{"lang":"eng","text":"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."}],"status":"public","external_id":{"arxiv":["2601.04083"]},"_id":"63530","department":[{"_id":"75"}],"user_id":"102868","language":[{"iso":"eng"}]},{"year":"2026","citation":{"bibtex":"@inproceedings{Shaaban KabakiboKabakibo_Trivedi_Wang_2026, title={Breaking the Ice: Analyzing Cold Start Latency in vLLM}, booktitle={The 9th Annual Conference on Machine Learning and Systems (MLSys)}, author={Shaaban KabakiboKabakibo, Huzaifa and Trivedi, Animesh and Wang, Lin}, year={2026} }","short":"H. Shaaban KabakiboKabakibo, A. Trivedi, L. Wang, in: The 9th Annual Conference on Machine Learning and Systems (MLSys), 2026.","mla":"Shaaban KabakiboKabakibo, Huzaifa, et al. “Breaking the Ice: Analyzing Cold Start Latency in VLLM.” <i>The 9th Annual Conference on Machine Learning and Systems (MLSys)</i>, 2026.","ama":"Shaaban KabakiboKabakibo H, Trivedi A, Wang L. Breaking the Ice: Analyzing Cold Start Latency in vLLM. In: <i>The 9th Annual Conference on Machine Learning and Systems (MLSys)</i>. ; 2026.","apa":"Shaaban KabakiboKabakibo, H., Trivedi, A., &#38; Wang, L. (2026). Breaking the Ice: Analyzing Cold Start Latency in vLLM. <i>The 9th Annual Conference on Machine Learning and Systems (MLSys)</i>. The 9th Annual Conference on Machine Learning and Systems (MLSys 2026) , Bellevue, WA.","ieee":"H. Shaaban KabakiboKabakibo, A. Trivedi, and L. Wang, “Breaking the Ice: Analyzing Cold Start Latency in vLLM,” presented at the The 9th Annual Conference on Machine Learning and Systems (MLSys 2026) , Bellevue, WA, 2026.","chicago":"Shaaban KabakiboKabakibo, Huzaifa, Animesh Trivedi, and Lin Wang. “Breaking the Ice: Analyzing Cold Start Latency in VLLM.” In <i>The 9th Annual Conference on Machine Learning and Systems (MLSys)</i>, 2026."},"date_updated":"2026-03-31T06:41:10Z","author":[{"last_name":"Shaaban KabakiboKabakibo","full_name":"Shaaban KabakiboKabakibo, Huzaifa","first_name":"Huzaifa"},{"last_name":"Trivedi","full_name":"Trivedi, Animesh","first_name":"Animesh"},{"last_name":"Wang","orcid":"0000-0001-7181-6128","full_name":"Wang, Lin","id":"102868","first_name":"Lin"}],"date_created":"2026-03-31T06:34:37Z","title":"Breaking the Ice: Analyzing Cold Start Latency in vLLM","conference":{"start_date":"2026-05-18","name":"The 9th Annual Conference on Machine Learning and Systems (MLSys 2026) ","location":"Bellevue, WA","end_date":"2026-05-22"},"publication":"The 9th Annual Conference on Machine Learning and Systems (MLSys)","type":"conference","status":"public","_id":"65249","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","language":[{"iso":"eng"}]},{"_id":"65250","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","language":[{"iso":"eng"}],"publication":"The 6th Workshop on Machine Learning and Systems (EuroMLSys)","type":"conference","status":"public","date_updated":"2026-03-31T06:39:41Z","author":[{"first_name":"Sepideh","last_name":"Zohdi","full_name":"Zohdi, Sepideh"},{"first_name":"Lin","last_name":"Wang","orcid":"0000-0001-7181-6128","id":"102868","full_name":"Wang, Lin"}],"date_created":"2026-03-31T06:38:34Z","title":"Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models ","conference":{"end_date":"2026-04-27","location":"Edinburg","name":"The 6th Workshop on Machine Learning and Systems (EuroMLSys)","start_date":"2026-04-27"},"year":"2026","citation":{"ieee":"S. Zohdi and L. Wang, “Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models ,” presented at the The 6th Workshop on Machine Learning and Systems (EuroMLSys), Edinburg, 2026.","chicago":"Zohdi, Sepideh, and Lin Wang. “Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models .” In <i>The 6th Workshop on Machine Learning and Systems (EuroMLSys)</i>, 2026.","ama":"Zohdi S, Wang L. Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models . In: <i>The 6th Workshop on Machine Learning and Systems (EuroMLSys)</i>. ; 2026.","apa":"Zohdi, S., &#38; Wang, L. (2026). Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models . <i>The 6th Workshop on Machine Learning and Systems (EuroMLSys)</i>. The 6th Workshop on Machine Learning and Systems (EuroMLSys), Edinburg.","bibtex":"@inproceedings{Zohdi_Wang_2026, title={Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models }, booktitle={The 6th Workshop on Machine Learning and Systems (EuroMLSys)}, author={Zohdi, Sepideh and Wang, Lin}, year={2026} }","short":"S. Zohdi, L. Wang, in: The 6th Workshop on Machine Learning and Systems (EuroMLSys), 2026.","mla":"Zohdi, Sepideh, and Lin Wang. “Before the First Token: Benchmarking Data Preprocessing in Vision-Language Models .” <i>The 6th Workshop on Machine Learning and Systems (EuroMLSys)</i>, 2026."}},{"language":[{"iso":"eng"}],"_id":"65013","user_id":"102868","department":[{"_id":"75"}],"status":"public","type":"conference","publication":"2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)","title":"Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning","date_updated":"2026-03-31T06:44:05Z","publisher":"IFIP","date_created":"2026-03-16T14:46:45Z","author":[{"first_name":"Marvin","last_name":"Illian","orcid":"0009-0007-2992-8346","id":"44169","full_name":"Illian, Marvin"},{"last_name":"Khalili","full_name":"Khalili, Ramin","first_name":"Ramin"},{"last_name":"A. de A. Rocha","full_name":"A. de A. Rocha, Antonio","first_name":"Antonio"},{"first_name":"Lin","full_name":"Wang, Lin","id":"102868","orcid":"0000-0001-7181-6128","last_name":"Wang"}],"year":"2026","citation":{"ama":"Illian M, Khalili R, A. de A. Rocha A, Wang L. Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning. In: <i>2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)</i>. IFIP; 2026.","ieee":"M. Illian, R. Khalili, A. A. de A. Rocha, and L. Wang, “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning,” 2026.","chicago":"Illian, Marvin, Ramin Khalili, Antonio A. de A. Rocha, and Lin Wang. “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning.” In <i>2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)</i>. IFIP, 2026.","bibtex":"@inproceedings{Illian_Khalili_A. de A. Rocha_Wang_2026, title={Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning}, booktitle={2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)}, publisher={IFIP}, author={Illian, Marvin and Khalili, Ramin and A. de A. Rocha, Antonio and Wang, Lin}, year={2026} }","mla":"Illian, Marvin, et al. “Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning.” <i>2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)</i>, IFIP, 2026.","short":"M. Illian, R. Khalili, A. A. de A. Rocha, L. Wang, in: 2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), IFIP, 2026.","apa":"Illian, M., Khalili, R., A. de A. Rocha, A., &#38; Wang, L. (2026). Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning. <i>2026 24th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)</i>."}},{"title":"Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices","doi":"10.1145/3680207.3765260","conference":{"start_date":"2025-11-04","name":"31st Annual International Conference on Mobile Computing and Networking (MobiCom)","location":"Hong Kong, China","end_date":"2025-11-08"},"publisher":"ACM","date_updated":"2025-12-12T08:08:49Z","date_created":"2025-12-12T08:06:10Z","author":[{"first_name":"Guilherme Henrique","last_name":"Apostolo","full_name":"Apostolo, Guilherme Henrique"},{"first_name":"Pablo","last_name":"Bauszat","full_name":"Bauszat, Pablo"},{"last_name":"Nigade","full_name":"Nigade, Vinod","first_name":"Vinod"},{"first_name":"Henri E.","last_name":"Bal","full_name":"Bal, Henri E."},{"orcid":"0000-0001-7181-6128","last_name":"Wang","full_name":"Wang, Lin","id":"102868","first_name":"Lin"}],"year":"2025","citation":{"chicago":"Apostolo, Guilherme Henrique, Pablo Bauszat, Vinod Nigade, Henri E. Bal, and Lin Wang. “Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices.” In <i>Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)</i>. ACM, 2025. <a href=\"https://doi.org/10.1145/3680207.3765260\">https://doi.org/10.1145/3680207.3765260</a>.","ieee":"G. H. Apostolo, P. Bauszat, V. Nigade, H. E. Bal, and L. Wang, “Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices,” presented at the 31st Annual International Conference on Mobile Computing and Networking (MobiCom), Hong Kong, China, 2025, doi: <a href=\"https://doi.org/10.1145/3680207.3765260\">10.1145/3680207.3765260</a>.","ama":"Apostolo GH, Bauszat P, Nigade V, Bal HE, Wang L. Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices. In: <i>Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)</i>. ACM; 2025. doi:<a href=\"https://doi.org/10.1145/3680207.3765260\">10.1145/3680207.3765260</a>","bibtex":"@inproceedings{Apostolo_Bauszat_Nigade_Bal_Wang_2025, title={Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices}, DOI={<a href=\"https://doi.org/10.1145/3680207.3765260\">10.1145/3680207.3765260</a>}, booktitle={Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)}, publisher={ACM}, author={Apostolo, Guilherme Henrique and Bauszat, Pablo and Nigade, Vinod and Bal, Henri E. and Wang, Lin}, year={2025} }","mla":"Apostolo, Guilherme Henrique, et al. “Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices.” <i>Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)</i>, ACM, 2025, doi:<a href=\"https://doi.org/10.1145/3680207.3765260\">10.1145/3680207.3765260</a>.","short":"G.H. Apostolo, P. Bauszat, V. Nigade, H.E. Bal, L. Wang, in: Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom), ACM, 2025.","apa":"Apostolo, G. H., Bauszat, P., Nigade, V., Bal, H. E., &#38; Wang, L. (2025). Uirapuru: Timely Video Analytics for High-Resolution Steerable Cameras on Edge Devices. <i>Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)</i>. 31st Annual International Conference on Mobile Computing and Networking (MobiCom), Hong Kong, China. <a href=\"https://doi.org/10.1145/3680207.3765260\">https://doi.org/10.1145/3680207.3765260</a>"},"publication_status":"published","language":[{"iso":"eng"}],"_id":"63054","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","status":"public","publication":"Proceedings of the 31st Annual International Conference on Mobile Computing and Networking (MobiCom)","type":"conference"},{"_id":"63057","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","language":[{"iso":"eng"}],"publication":"IEEE Transactions on Sustainable Computing","type":"journal_article","status":"public","date_updated":"2025-12-12T08:14:11Z","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","volume":10,"author":[{"full_name":"Pei, Qiangyu","last_name":"Pei","first_name":"Qiangyu"},{"last_name":"Yuan","full_name":"Yuan, Yongjie","first_name":"Yongjie"},{"first_name":"Haichuan","last_name":"Hu","full_name":"Hu, Haichuan"},{"id":"102868","full_name":"Wang, Lin","orcid":"0000-0001-7181-6128","last_name":"Wang","first_name":"Lin"},{"first_name":"Dong","last_name":"Zhang","full_name":"Zhang, Dong"},{"full_name":"Yan, Bingheng","last_name":"Yan","first_name":"Bingheng"},{"full_name":"Yu, Chen","last_name":"Yu","first_name":"Chen"},{"last_name":"Liu","full_name":"Liu, Fangming","first_name":"Fangming"}],"date_created":"2025-12-12T08:13:53Z","title":"Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters","doi":"10.1109/tsusc.2025.3542563","publication_identifier":{"issn":["2377-3782","2377-3790"]},"publication_status":"published","issue":"4","year":"2025","page":"804-819","intvolume":"        10","citation":{"apa":"Pei, Q., Yuan, Y., Hu, H., Wang, L., Zhang, D., Yan, B., Yu, C., &#38; Liu, F. (2025). Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters. <i>IEEE Transactions on Sustainable Computing</i>, <i>10</i>(4), 804–819. <a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">https://doi.org/10.1109/tsusc.2025.3542563</a>","bibtex":"@article{Pei_Yuan_Hu_Wang_Zhang_Yan_Yu_Liu_2025, title={Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters}, volume={10}, DOI={<a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">10.1109/tsusc.2025.3542563</a>}, number={4}, journal={IEEE Transactions on Sustainable Computing}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Pei, Qiangyu and Yuan, Yongjie and Hu, Haichuan and Wang, Lin and Zhang, Dong and Yan, Bingheng and Yu, Chen and Liu, Fangming}, year={2025}, pages={804–819} }","mla":"Pei, Qiangyu, et al. “Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters.” <i>IEEE Transactions on Sustainable Computing</i>, vol. 10, no. 4, Institute of Electrical and Electronics Engineers (IEEE), 2025, pp. 804–19, doi:<a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">10.1109/tsusc.2025.3542563</a>.","short":"Q. Pei, Y. Yuan, H. Hu, L. Wang, D. Zhang, B. Yan, C. Yu, F. Liu, IEEE Transactions on Sustainable Computing 10 (2025) 804–819.","ama":"Pei Q, Yuan Y, Hu H, et al. Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters. <i>IEEE Transactions on Sustainable Computing</i>. 2025;10(4):804-819. doi:<a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">10.1109/tsusc.2025.3542563</a>","ieee":"Q. Pei <i>et al.</i>, “Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters,” <i>IEEE Transactions on Sustainable Computing</i>, vol. 10, no. 4, pp. 804–819, 2025, doi: <a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">10.1109/tsusc.2025.3542563</a>.","chicago":"Pei, Qiangyu, Yongjie Yuan, Haichuan Hu, Lin Wang, Dong Zhang, Bingheng Yan, Chen Yu, and Fangming Liu. “Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters.” <i>IEEE Transactions on Sustainable Computing</i> 10, no. 4 (2025): 804–19. <a href=\"https://doi.org/10.1109/tsusc.2025.3542563\">https://doi.org/10.1109/tsusc.2025.3542563</a>."}},{"date_updated":"2025-12-12T08:13:18Z","publisher":"IEEE","date_created":"2025-12-12T08:12:48Z","author":[{"full_name":"Wu, Jing","last_name":"Wu","first_name":"Jing"},{"first_name":"Lin","full_name":"Wang, Lin","id":"102868","orcid":"0000-0001-7181-6128","last_name":"Wang"},{"full_name":"Deng, Quanfeng","last_name":"Deng","first_name":"Quanfeng"},{"last_name":"Yu","full_name":"Yu, Chen","first_name":"Chen"},{"first_name":"Dong","last_name":"Zhang","full_name":"Zhang, Dong"},{"last_name":"Yan","full_name":"Yan, Bingheng","first_name":"Bingheng"},{"full_name":"Liu, Fangming","last_name":"Liu","first_name":"Fangming"}],"title":"It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation","conference":{"location":"Milan, Italy","name":"2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"},"doi":"10.1109/ipdps64566.2025.00012","publication_status":"published","year":"2025","citation":{"apa":"Wu, J., Wang, L., Deng, Q., Yu, C., Zhang, D., Yan, B., &#38; Liu, F. (2025). It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation. <i>2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)</i>. 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Milan, Italy. <a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">https://doi.org/10.1109/ipdps64566.2025.00012</a>","bibtex":"@inproceedings{Wu_Wang_Deng_Yu_Zhang_Yan_Liu_2025, title={It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation}, DOI={<a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">10.1109/ipdps64566.2025.00012</a>}, booktitle={2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, publisher={IEEE}, author={Wu, Jing and Wang, Lin and Deng, Quanfeng and Yu, Chen and Zhang, Dong and Yan, Bingheng and Liu, Fangming}, year={2025} }","short":"J. Wu, L. Wang, Q. Deng, C. Yu, D. Zhang, B. Yan, F. Liu, in: 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2025.","mla":"Wu, Jing, et al. “It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation.” <i>2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)</i>, IEEE, 2025, doi:<a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">10.1109/ipdps64566.2025.00012</a>.","chicago":"Wu, Jing, Lin Wang, Quanfeng Deng, Chen Yu, Dong Zhang, Bingheng Yan, and Fangming Liu. “It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation.” In <i>2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)</i>. IEEE, 2025. <a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">https://doi.org/10.1109/ipdps64566.2025.00012</a>.","ieee":"J. Wu <i>et al.</i>, “It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation,” presented at the 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Milan, Italy, 2025, doi: <a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">10.1109/ipdps64566.2025.00012</a>.","ama":"Wu J, Wang L, Deng Q, et al. It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation. In: <i>2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)</i>. IEEE; 2025. doi:<a href=\"https://doi.org/10.1109/ipdps64566.2025.00012\">10.1109/ipdps64566.2025.00012</a>"},"_id":"63056","user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"language":[{"iso":"eng"}],"type":"conference","publication":"2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","status":"public"},{"status":"public","type":"conference","publication":"Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)","language":[{"iso":"eng"}],"user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"_id":"61256","citation":{"ieee":"M. Illian, B. Luchterhandt, and L. Wang, “Band Switching for Mobile Energy Optimization in 5G Networks and Beyond,” presented at the ACM Workshop on Mobility in the Evolving Internet Architecture (MobiArch), co-located with ACM MobiCom, Hong Kong, China, 2025, doi: <a href=\"https://doi.org/10.1145/3737897.3767294\">10.1145/3737897.3767294</a>.","chicago":"Illian, Marvin, Björn Luchterhandt, and Lin Wang. “Band Switching for Mobile Energy Optimization in 5G Networks and Beyond.” In <i>Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)</i>, 2025. <a href=\"https://doi.org/10.1145/3737897.3767294\">https://doi.org/10.1145/3737897.3767294</a>.","ama":"Illian M, Luchterhandt B, Wang L. Band Switching for Mobile Energy Optimization in 5G Networks and Beyond. In: <i>Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)</i>. ; 2025. doi:<a href=\"https://doi.org/10.1145/3737897.3767294\">10.1145/3737897.3767294</a>","apa":"Illian, M., Luchterhandt, B., &#38; Wang, L. (2025). Band Switching for Mobile Energy Optimization in 5G Networks and Beyond. <i>Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)</i>. ACM Workshop on Mobility in the Evolving Internet Architecture (MobiArch), co-located with ACM MobiCom, Hong Kong, China. <a href=\"https://doi.org/10.1145/3737897.3767294\">https://doi.org/10.1145/3737897.3767294</a>","mla":"Illian, Marvin, et al. “Band Switching for Mobile Energy Optimization in 5G Networks and Beyond.” <i>Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)</i>, 2025, doi:<a href=\"https://doi.org/10.1145/3737897.3767294\">10.1145/3737897.3767294</a>.","bibtex":"@inproceedings{Illian_Luchterhandt_Wang_2025, title={Band Switching for Mobile Energy Optimization in 5G Networks and Beyond}, DOI={<a href=\"https://doi.org/10.1145/3737897.3767294\">10.1145/3737897.3767294</a>}, booktitle={Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch)}, author={Illian, Marvin and Luchterhandt, Björn and Wang, Lin}, year={2025} }","short":"M. Illian, B. Luchterhandt, L. Wang, in: Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture (MobiArch), 2025."},"year":"2025","conference":{"end_date":"2025-11-08","location":"Hong Kong, China","name":"ACM Workshop on Mobility in the Evolving Internet Architecture (MobiArch), co-located with ACM MobiCom","start_date":"2025-11-04"},"doi":"10.1145/3737897.3767294","title":"Band Switching for Mobile Energy Optimization in 5G Networks and Beyond","date_created":"2025-09-12T11:22:18Z","author":[{"first_name":"Marvin","last_name":"Illian","orcid":"0009-0007-2992-8346","full_name":"Illian, Marvin","id":"44169"},{"full_name":"Luchterhandt, Björn","last_name":"Luchterhandt","first_name":"Björn"},{"full_name":"Wang, Lin","id":"102868","last_name":"Wang","orcid":"0000-0001-7181-6128","first_name":"Lin"}],"date_updated":"2025-12-12T08:11:38Z"},{"year":"2025","citation":{"chicago":"Ghafouri, Saeid, Kamran Razavi, Mehran Salmani, Alireza Sanaee, Tania Lorido Botran, Lin Wang, Joseph Doyle, and Pooyan Jamshidi. “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.” In <i>Companion of the 16th ACM/SPEC International Conference on Performance Engineering</i>. ACM, 2025. <a href=\"https://doi.org/10.1145/3680256.3721266\">https://doi.org/10.1145/3680256.3721266</a>.","ieee":"S. Ghafouri <i>et al.</i>, “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency,” presented at the 16th ACM/SPEC International Conference on Performance Engineering, 2025, doi: <a href=\"https://doi.org/10.1145/3680256.3721266\">10.1145/3680256.3721266</a>.","ama":"Ghafouri S, Razavi K, Salmani M, et al. IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency. In: <i>Companion of the 16th ACM/SPEC International Conference on Performance Engineering</i>. ACM; 2025. doi:<a href=\"https://doi.org/10.1145/3680256.3721266\">10.1145/3680256.3721266</a>","short":"S. Ghafouri, K. Razavi, M. Salmani, A. Sanaee, T.L. Botran, L. Wang, J. Doyle, P. Jamshidi, in: Companion of the 16th ACM/SPEC International Conference on Performance Engineering, ACM, 2025.","bibtex":"@inproceedings{Ghafouri_Razavi_Salmani_Sanaee_Botran_Wang_Doyle_Jamshidi_2025, title={IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency}, DOI={<a href=\"https://doi.org/10.1145/3680256.3721266\">10.1145/3680256.3721266</a>}, booktitle={Companion of the 16th ACM/SPEC International Conference on Performance Engineering}, publisher={ACM}, 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}, year={2025} }","mla":"Ghafouri, Saeid, et al. “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.” <i>Companion of the 16th ACM/SPEC International Conference on Performance Engineering</i>, ACM, 2025, doi:<a href=\"https://doi.org/10.1145/3680256.3721266\">10.1145/3680256.3721266</a>.","apa":"Ghafouri, S., Razavi, K., Salmani, M., Sanaee, A., Botran, T. L., Wang, L., Doyle, J., &#38; Jamshidi, P. (2025). IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency. <i>Companion of the 16th ACM/SPEC International Conference on Performance Engineering</i>. 16th ACM/SPEC International Conference on Performance Engineering. <a href=\"https://doi.org/10.1145/3680256.3721266\">https://doi.org/10.1145/3680256.3721266</a>"},"publication_status":"published","title":"IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency","conference":{"name":"16th ACM/SPEC International Conference on Performance Engineering"},"doi":"10.1145/3680256.3721266","date_updated":"2025-12-12T08:18:15Z","publisher":"ACM","author":[{"first_name":"Saeid","last_name":"Ghafouri","full_name":"Ghafouri, Saeid"},{"first_name":"Kamran","full_name":"Razavi, Kamran","last_name":"Razavi"},{"first_name":"Mehran","full_name":"Salmani, Mehran","last_name":"Salmani"},{"first_name":"Alireza","last_name":"Sanaee","full_name":"Sanaee, Alireza"},{"first_name":"Tania Lorido","last_name":"Botran","full_name":"Botran, Tania Lorido"},{"first_name":"Lin","orcid":"0000-0001-7181-6128","last_name":"Wang","full_name":"Wang, Lin","id":"102868"},{"last_name":"Doyle","full_name":"Doyle, Joseph","first_name":"Joseph"},{"first_name":"Pooyan","full_name":"Jamshidi, Pooyan","last_name":"Jamshidi"}],"date_created":"2025-12-12T08:14:50Z","status":"public","publication":"Companion of the 16th ACM/SPEC International Conference on Performance Engineering","type":"conference","language":[{"iso":"eng"}],"_id":"63058","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868"},{"language":[{"iso":"eng"}],"user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"_id":"50807","status":"public","type":"conference","publication":"Proceedings of the ACM Web Conference (WWW)","conference":{"location":"Singapore","end_date":"2024-05-17","start_date":"2024-05-13","name":"ACM Web Conference (WWW)"},"doi":"10.1145/3589334.3645383","title":"𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing","date_created":"2024-01-23T20:34:27Z","author":[{"full_name":"Hu, Haichuan","last_name":"Hu","first_name":"Haichuan"},{"full_name":"Liu, Fangming","last_name":"Liu","first_name":"Fangming"},{"full_name":"Pei, Qiangyu","last_name":"Pei","first_name":"Qiangyu"},{"full_name":"Yuan, Yongjie","last_name":"Yuan","first_name":"Yongjie"},{"full_name":"Xu, Zichen","last_name":"Xu","first_name":"Zichen"},{"first_name":"Lin","full_name":"Wang, Lin","id":"102868","last_name":"Wang"}],"publisher":"ACM","date_updated":"2024-07-23T19:51:27Z","citation":{"short":"H. Hu, F. Liu, Q. Pei, Y. Yuan, Z. Xu, L. Wang, in: Proceedings of the ACM Web Conference (WWW), ACM, 2024.","mla":"Hu, Haichuan, et al. “𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing.” <i>Proceedings of the ACM Web Conference (WWW)</i>, ACM, 2024, doi:<a href=\"https://doi.org/10.1145/3589334.3645383\">10.1145/3589334.3645383</a>.","bibtex":"@inproceedings{Hu_Liu_Pei_Yuan_Xu_Wang_2024, title={𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing}, DOI={<a href=\"https://doi.org/10.1145/3589334.3645383\">10.1145/3589334.3645383</a>}, booktitle={Proceedings of the ACM Web Conference (WWW)}, publisher={ACM}, author={Hu, Haichuan and Liu, Fangming and Pei, Qiangyu and Yuan, Yongjie and Xu, Zichen and Wang, Lin}, year={2024} }","apa":"Hu, H., Liu, F., Pei, Q., Yuan, Y., Xu, Z., &#38; Wang, L. (2024). 𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing. <i>Proceedings of the ACM Web Conference (WWW)</i>. ACM Web Conference (WWW), Singapore. <a href=\"https://doi.org/10.1145/3589334.3645383\">https://doi.org/10.1145/3589334.3645383</a>","ama":"Hu H, Liu F, Pei Q, Yuan Y, Xu Z, Wang L. 𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing. In: <i>Proceedings of the ACM Web Conference (WWW)</i>. ACM; 2024. doi:<a href=\"https://doi.org/10.1145/3589334.3645383\">10.1145/3589334.3645383</a>","chicago":"Hu, Haichuan, Fangming Liu, Qiangyu Pei, Yongjie Yuan, Zichen Xu, and Lin Wang. “𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing.” In <i>Proceedings of the ACM Web Conference (WWW)</i>. ACM, 2024. <a href=\"https://doi.org/10.1145/3589334.3645383\">https://doi.org/10.1145/3589334.3645383</a>.","ieee":"H. Hu, F. Liu, Q. Pei, Y. Yuan, Z. Xu, and L. Wang, “𝜆Grapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing,” presented at the ACM Web Conference (WWW), Singapore, 2024, doi: <a href=\"https://doi.org/10.1145/3589334.3645383\">10.1145/3589334.3645383</a>."},"year":"2024"},{"status":"public","publication":"Journal of Systems Research (JSys)","type":"journal_article","language":[{"iso":"eng"}],"department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","_id":"53531","citation":{"ieee":"S. Ghafouri <i>et al.</i>, “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency,” <i>Journal of Systems Research (JSys)</i>.","chicago":"Ghafouri, Saeid, Kamran Razavi, Mehran Salmani, Alireza Sanaee, Tania  Lorido Botran, Lin Wang, Joseph Doyle, and Pooyan Jamshidi. “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.” <i>Journal of Systems Research (JSys)</i>, n.d.","ama":"Ghafouri S, Razavi K, Salmani M, et al. IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency. <i>Journal of Systems Research (JSys)</i>.","apa":"Ghafouri, S., Razavi, K., Salmani, M., Sanaee, A., Lorido Botran, T., Wang, L., Doyle, J., &#38; Jamshidi, P. (n.d.). IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency. <i>Journal of Systems Research (JSys)</i>.","mla":"Ghafouri, Saeid, et al. “IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency.” <i>Journal of Systems Research (JSys)</i>.","short":"S. Ghafouri, K. Razavi, M. Salmani, A. Sanaee, T. Lorido Botran, L. Wang, J. Doyle, P. Jamshidi, Journal of Systems Research (JSys) (n.d.).","bibtex":"@article{Ghafouri_Razavi_Salmani_Sanaee_Lorido Botran_Wang_Doyle_Jamshidi, title={IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency}, journal={Journal of Systems Research (JSys)}, 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} }"},"year":"2024","publication_status":"accepted","title":"IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency","author":[{"first_name":"Saeid","full_name":"Ghafouri, Saeid","last_name":"Ghafouri"},{"full_name":"Razavi, Kamran","last_name":"Razavi","first_name":"Kamran"},{"full_name":"Salmani, Mehran","last_name":"Salmani","first_name":"Mehran"},{"first_name":"Alireza","last_name":"Sanaee","full_name":"Sanaee, Alireza"},{"last_name":"Lorido Botran","full_name":"Lorido Botran, Tania ","first_name":"Tania "},{"first_name":"Lin","last_name":"Wang","full_name":"Wang, Lin","id":"102868"},{"last_name":"Doyle","full_name":"Doyle, Joseph","first_name":"Joseph"},{"last_name":"Jamshidi","full_name":"Jamshidi, Pooyan","first_name":"Pooyan"}],"date_created":"2024-04-16T18:41:14Z","date_updated":"2024-07-23T20:00:14Z"},{"conference":{"start_date":"2024-06-26","name":"29th IEEE International Symposium on Computers and Communications (ISCC)","location":"Paris, France","end_date":"2024-06-29"},"title":"NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award)","date_created":"2024-07-23T19:55:16Z","author":[{"last_name":"Razavi","full_name":"Razavi, Kamran","first_name":"Kamran"},{"first_name":"Shayan","full_name":"Davari Fard, Shayan","last_name":"Davari Fard"},{"first_name":"George","last_name":"Karlos","full_name":"Karlos, George"},{"last_name":"Nigade","full_name":"Nigade, Vinod","first_name":"Vinod"},{"full_name":"Mühlhäuser, Max","last_name":"Mühlhäuser","first_name":"Max"},{"id":"102868","full_name":"Wang, Lin","last_name":"Wang","first_name":"Lin"}],"date_updated":"2024-08-28T13:56:18Z","citation":{"ama":"Razavi K, Davari Fard S, Karlos G, Nigade V, Mühlhäuser M, Wang L. NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award). In: <i>Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)</i>. ; 2024.","chicago":"Razavi, Kamran, Shayan Davari Fard, George Karlos, Vinod Nigade, Max Mühlhäuser, and Lin Wang. “NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award).” In <i>Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)</i>, 2024.","ieee":"K. Razavi, S. Davari Fard, G. Karlos, V. Nigade, M. Mühlhäuser, and L. Wang, “NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award),” presented at the 29th IEEE International Symposium on Computers and Communications (ISCC), Paris, France, 2024.","apa":"Razavi, K., Davari Fard, S., Karlos, G., Nigade, V., Mühlhäuser, M., &#38; Wang, L. (2024). NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award). <i>Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)</i>. 29th IEEE International Symposium on Computers and Communications (ISCC), Paris, France.","short":"K. Razavi, S. Davari Fard, G. Karlos, V. Nigade, M. Mühlhäuser, L. Wang, in: Proceedings of the IEEE International Symposium on Computers and Communications (ISCC), 2024.","bibtex":"@inproceedings{Razavi_Davari Fard_Karlos_Nigade_Mühlhäuser_Wang_2024, title={NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award)}, booktitle={Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)}, author={Razavi, Kamran and Davari Fard, Shayan and Karlos, George and Nigade, Vinod and Mühlhäuser, Max and Wang, Lin}, year={2024} }","mla":"Razavi, Kamran, et al. “NetNN: Neural Intrusion Detection System in Programmable Networks (Second Best Paper Award).” <i>Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)</i>, 2024."},"year":"2024","language":[{"iso":"eng"}],"user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"_id":"55365","status":"public","type":"conference","publication":"Proceedings of the IEEE International Symposium on Computers and Communications (ISCC)"},{"date_created":"2024-03-28T12:00:49Z","author":[{"first_name":"Kamran","last_name":"Razavi","full_name":"Razavi, Kamran"},{"first_name":"Saeid","last_name":"Ghafouri","full_name":"Ghafouri, Saeid"},{"full_name":"Mühlhäuser, Max","last_name":"Mühlhäuser","first_name":"Max"},{"full_name":"Jamshidi, Pooyan","last_name":"Jamshidi","first_name":"Pooyan"},{"first_name":"Lin","full_name":"Wang, Lin","id":"102868","last_name":"Wang"}],"date_updated":"2024-08-28T14:00:46Z","publisher":"ACM","conference":{"location":"Athens, Greece","end_date":"2024-04-22","start_date":"2024-04-22","name":"4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024"},"doi":"10.1145/3642970.365583","title":"Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling","citation":{"chicago":"Razavi, Kamran, Saeid Ghafouri, Max Mühlhäuser, Pooyan Jamshidi, and Lin Wang. “Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling.” In <i>Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with EuroSys 2024</i>. ACM, 2024. <a href=\"https://doi.org/10.1145/3642970.365583\">https://doi.org/10.1145/3642970.365583</a>.","ieee":"K. Razavi, S. Ghafouri, M. Mühlhäuser, P. Jamshidi, and L. Wang, “Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling,” presented at the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024, Athens, Greece, 2024, doi: <a href=\"https://doi.org/10.1145/3642970.365583\">10.1145/3642970.365583</a>.","ama":"Razavi K, Ghafouri S, Mühlhäuser M, Jamshidi P, Wang L. Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling. In: <i>Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with EuroSys 2024</i>. ACM; 2024. doi:<a href=\"https://doi.org/10.1145/3642970.365583\">10.1145/3642970.365583</a>","apa":"Razavi, K., Ghafouri, S., Mühlhäuser, M., Jamshidi, P., &#38; Wang, L. (2024). Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling. <i>Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with EuroSys 2024</i>. 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024, Athens, Greece. <a href=\"https://doi.org/10.1145/3642970.365583\">https://doi.org/10.1145/3642970.365583</a>","short":"K. Razavi, S. Ghafouri, M. Mühlhäuser, P. Jamshidi, L. Wang, in: Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with EuroSys 2024, ACM, 2024.","bibtex":"@inproceedings{Razavi_Ghafouri_Mühlhäuser_Jamshidi_Wang_2024, title={Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling}, DOI={<a href=\"https://doi.org/10.1145/3642970.365583\">10.1145/3642970.365583</a>}, booktitle={Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024}, publisher={ACM}, author={Razavi, Kamran and Ghafouri, Saeid and Mühlhäuser, Max and Jamshidi, Pooyan and Wang, Lin}, year={2024} }","mla":"Razavi, Kamran, et al. “Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling.” <i>Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), Colocated with EuroSys 2024</i>, ACM, 2024, doi:<a href=\"https://doi.org/10.1145/3642970.365583\">10.1145/3642970.365583</a>."},"year":"2024","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","_id":"53095","language":[{"iso":"eng"}],"publication":"Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024","type":"conference","status":"public"},{"publication_status":"accepted","citation":{"mla":"Dou, Feng, et al. “X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics.” <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>, IEEE, doi:<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">10.1109/INFOCOM52122.2024.10621341</a>.","short":"F. Dou, L. Wang, S. Chen, F. Liu, in: Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), IEEE, n.d.","bibtex":"@inproceedings{Dou_Wang_Chen_Liu, title={X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics}, DOI={<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">10.1109/INFOCOM52122.2024.10621341</a>}, booktitle={Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}, publisher={IEEE}, author={Dou, Feng and Wang, Lin and Chen, Shutong and Liu, Fangming} }","apa":"Dou, F., Wang, L., Chen, S., &#38; Liu, F. (n.d.). X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics. <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada. <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">https://doi.org/10.1109/INFOCOM52122.2024.10621341</a>","ama":"Dou F, Wang L, Chen S, Liu F. X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics. In: <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE. doi:<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">10.1109/INFOCOM52122.2024.10621341</a>","ieee":"F. Dou, L. Wang, S. Chen, and F. Liu, “X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics,” presented at the IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, doi: <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">10.1109/INFOCOM52122.2024.10621341</a>.","chicago":"Dou, Feng, Lin Wang, Shutong Chen, and Fangming Liu. “X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics.” In <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE, n.d. <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621341\">https://doi.org/10.1109/INFOCOM52122.2024.10621341</a>."},"year":"2024","author":[{"full_name":"Dou, Feng","last_name":"Dou","first_name":"Feng"},{"last_name":"Wang","id":"102868","full_name":"Wang, Lin","first_name":"Lin"},{"last_name":"Chen","full_name":"Chen, Shutong","first_name":"Shutong"},{"full_name":"Liu, Fangming","last_name":"Liu","first_name":"Fangming"}],"date_created":"2023-12-22T20:24:27Z","publisher":"IEEE","date_updated":"2024-08-28T13:59:14Z","doi":"10.1109/INFOCOM52122.2024.10621341","conference":{"location":"Vancouver, Canada","end_date":"2024-05-23","start_date":"2024-05-20","name":"IEEE International Conference on Computer Communications (INFOCOM)"},"title":"X-Stream: A Flexible, Adaptive Video Transformer for Privacy-Preserving Video Stream Analytics","publication":"Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)","type":"conference","status":"public","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","_id":"50066","language":[{"iso":"eng"}]},{"year":"2024","citation":{"short":"G. Liu, V. Nigade, H. Bal, L. Wang, in: Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET), 2024.","bibtex":"@inproceedings{Liu_Nigade_Bal_Wang_2024, title={A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT}, DOI={<a href=\"https://doi.org/10.1145/3663408.3663414\">10.1145/3663408.3663414</a>}, booktitle={Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)}, author={Liu, Gaosheng and Nigade, Vinod and Bal, Henri and Wang, Lin}, year={2024} }","mla":"Liu, Gaosheng, et al. “A Little Certainty Is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT.” <i>Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)</i>, 2024, doi:<a href=\"https://doi.org/10.1145/3663408.3663414\">10.1145/3663408.3663414</a>.","apa":"Liu, G., Nigade, V., Bal, H., &#38; Wang, L. (2024). A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT. <i>Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)</i>. ACM Asia Pacific Workshop on Networking (APNET), Sydney, Austrialia. <a href=\"https://doi.org/10.1145/3663408.3663414\">https://doi.org/10.1145/3663408.3663414</a>","chicago":"Liu, Gaosheng, Vinod Nigade, Henri Bal, and Lin Wang. “A Little Certainty Is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT.” In <i>Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)</i>, 2024. <a href=\"https://doi.org/10.1145/3663408.3663414\">https://doi.org/10.1145/3663408.3663414</a>.","ieee":"G. Liu, V. Nigade, H. Bal, and L. Wang, “A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT,” presented at the ACM Asia Pacific Workshop on Networking (APNET), Sydney, Austrialia, 2024, doi: <a href=\"https://doi.org/10.1145/3663408.3663414\">10.1145/3663408.3663414</a>.","ama":"Liu G, Nigade V, Bal H, Wang L. A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT. In: <i>Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)</i>. ; 2024. doi:<a href=\"https://doi.org/10.1145/3663408.3663414\">10.1145/3663408.3663414</a>"},"title":"A Little Certainty is All We Need: Discovery and Synchronization Acceleration in Battery-Free IoT","doi":"10.1145/3663408.3663414","conference":{"location":"Sydney, Austrialia","end_date":"2024-08-04","start_date":"2024-08-03","name":"ACM Asia Pacific Workshop on Networking (APNET)"},"date_updated":"2024-08-28T13:58:10Z","date_created":"2024-04-30T18:25:22Z","author":[{"last_name":"Liu","full_name":"Liu, Gaosheng","first_name":"Gaosheng"},{"first_name":"Vinod","full_name":"Nigade, Vinod","last_name":"Nigade"},{"last_name":"Bal","full_name":"Bal, Henri","first_name":"Henri"},{"id":"102868","full_name":"Wang, Lin","last_name":"Wang","first_name":"Lin"}],"status":"public","type":"conference","publication":"Proceedings of the 8th ACM Asia Pacific Workshop on Networking (APNET)","language":[{"iso":"eng"}],"_id":"53807","user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}]},{"year":"2024","citation":{"apa":"Karlos, G., Bal, H., &#38; Wang, L. (2024). NetCL: A Unified Programming Framework for In-Network Computing. <i>Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)</i>. International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), Atlanta, GA.","mla":"Karlos, George, et al. “NetCL: A Unified Programming Framework for In-Network Computing.” <i>Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)</i>, 2024.","short":"G. Karlos, H. Bal, L. Wang, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2024.","bibtex":"@inproceedings{Karlos_Bal_Wang_2024, title={NetCL: A Unified Programming Framework for In-Network Computing}, booktitle={Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)}, author={Karlos, George and Bal, Henri and Wang, Lin}, year={2024} }","ama":"Karlos G, Bal H, Wang L. NetCL: A Unified Programming Framework for In-Network Computing. In: <i>Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)</i>. ; 2024.","chicago":"Karlos, George, Henri Bal, and Lin Wang. “NetCL: A Unified Programming Framework for In-Network Computing.” In <i>Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)</i>, 2024.","ieee":"G. Karlos, H. Bal, and L. Wang, “NetCL: A Unified Programming Framework for In-Network Computing,” presented at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), Atlanta, GA, 2024."},"title":"NetCL: A Unified Programming Framework for In-Network Computing","conference":{"end_date":"2024-11-22","location":"Atlanta, GA","name":"International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)","start_date":"2024-11-17"},"date_updated":"2024-08-28T13:57:13Z","author":[{"full_name":"Karlos, George","last_name":"Karlos","first_name":"George"},{"first_name":"Henri","last_name":"Bal","full_name":"Bal, Henri"},{"last_name":"Wang","full_name":"Wang, Lin","id":"102868","first_name":"Lin"}],"date_created":"2024-07-23T19:57:00Z","status":"public","type":"conference","publication":"Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)","language":[{"iso":"eng"}],"_id":"55366","user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}]},{"_id":"55364","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"user_id":"102868","language":[{"iso":"eng"}],"publication":"IEEE Transactions on Mobile Computing (TMC)","type":"journal_article","status":"public","date_updated":"2024-08-28T14:01:21Z","date_created":"2024-07-23T19:50:41Z","author":[{"full_name":"Liu, Gaosheng","last_name":"Liu","first_name":"Gaosheng"},{"first_name":"Lin","last_name":"Wang","full_name":"Wang, Lin","id":"102868"}],"title":"Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing","doi":"10.1109/TMC.2024.3429636","year":"2024","citation":{"bibtex":"@article{Liu_Wang_2024, title={Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing}, DOI={<a href=\"https://doi.org/10.1109/TMC.2024.3429636\">10.1109/TMC.2024.3429636</a>}, journal={IEEE Transactions on Mobile Computing (TMC)}, author={Liu, Gaosheng and Wang, Lin}, year={2024} }","mla":"Liu, Gaosheng, and Lin Wang. “Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing.” <i>IEEE Transactions on Mobile Computing (TMC)</i>, 2024, doi:<a href=\"https://doi.org/10.1109/TMC.2024.3429636\">10.1109/TMC.2024.3429636</a>.","short":"G. Liu, L. Wang, IEEE Transactions on Mobile Computing (TMC) (2024).","apa":"Liu, G., &#38; Wang, L. (2024). Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing. <i>IEEE Transactions on Mobile Computing (TMC)</i>. <a href=\"https://doi.org/10.1109/TMC.2024.3429636\">https://doi.org/10.1109/TMC.2024.3429636</a>","ama":"Liu G, Wang L. Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing. <i>IEEE Transactions on Mobile Computing (TMC)</i>. Published online 2024. doi:<a href=\"https://doi.org/10.1109/TMC.2024.3429636\">10.1109/TMC.2024.3429636</a>","ieee":"G. Liu and L. Wang, “Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing,” <i>IEEE Transactions on Mobile Computing (TMC)</i>, 2024, doi: <a href=\"https://doi.org/10.1109/TMC.2024.3429636\">10.1109/TMC.2024.3429636</a>.","chicago":"Liu, Gaosheng, and Lin Wang. “Data On the Go: Seamless Data Routing for Intermittently-Powered Battery-Free Sensing.” <i>IEEE Transactions on Mobile Computing (TMC)</i>, 2024. <a href=\"https://doi.org/10.1109/TMC.2024.3429636\">https://doi.org/10.1109/TMC.2024.3429636</a>."}},{"publication_status":"accepted","citation":{"mla":"Blöcher, Marcel, et al. “Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES.” <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>, IEEE, doi:<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">10.1109/INFOCOM52122.2024.10621125</a>.","bibtex":"@inproceedings{Blöcher_Nedderhut_Chuprikov_Khalili_Eugster_Wang, title={Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES}, DOI={<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">10.1109/INFOCOM52122.2024.10621125</a>}, booktitle={Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)}, publisher={IEEE}, author={Blöcher, Marcel and Nedderhut, Nils and Chuprikov, Pavel and Khalili, Ramin and Eugster, Patrick and Wang, Lin} }","short":"M. Blöcher, N. Nedderhut, P. Chuprikov, R. Khalili, P. Eugster, L. Wang, in: Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), IEEE, n.d.","apa":"Blöcher, M., Nedderhut, N., Chuprikov, P., Khalili, R., Eugster, P., &#38; Wang, L. (n.d.). Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES. <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada. <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">https://doi.org/10.1109/INFOCOM52122.2024.10621125</a>","ieee":"M. Blöcher, N. Nedderhut, P. Chuprikov, R. Khalili, P. Eugster, and L. Wang, “Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES,” presented at the IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, doi: <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">10.1109/INFOCOM52122.2024.10621125</a>.","chicago":"Blöcher, Marcel, Nils Nedderhut, Pavel Chuprikov, Ramin Khalili, Patrick Eugster, and Lin Wang. “Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES.” In <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE, n.d. <a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">https://doi.org/10.1109/INFOCOM52122.2024.10621125</a>.","ama":"Blöcher M, Nedderhut N, Chuprikov P, Khalili R, Eugster P, Wang L. Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES. In: <i>Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)</i>. IEEE. doi:<a href=\"https://doi.org/10.1109/INFOCOM52122.2024.10621125\">10.1109/INFOCOM52122.2024.10621125</a>"},"year":"2024","date_created":"2023-12-22T20:06:42Z","author":[{"last_name":"Blöcher","full_name":"Blöcher, Marcel","first_name":"Marcel"},{"last_name":"Nedderhut","full_name":"Nedderhut, Nils","first_name":"Nils"},{"first_name":"Pavel","full_name":"Chuprikov, Pavel","last_name":"Chuprikov"},{"first_name":"Ramin","full_name":"Khalili, Ramin","last_name":"Khalili"},{"first_name":"Patrick","full_name":"Eugster, Patrick","last_name":"Eugster"},{"first_name":"Lin","id":"102868","full_name":"Wang, Lin","last_name":"Wang"}],"publisher":"IEEE","date_updated":"2024-10-20T15:51:43Z","doi":"10.1109/INFOCOM52122.2024.10621125","conference":{"start_date":"2024-05-20","name":"IEEE International Conference on Computer Communications (INFOCOM)","location":"Vancouver, Canada","end_date":"2024-05-23"},"title":"Train Once Apply Anywhere: Effective Scheduling for Network Function Chains Running on FUMES","publication":"Proceedings of the IEEE International Conference on Computer Communications (INFOCOM)","type":"conference","status":"public","department":[{"_id":"75"}],"user_id":"102868","_id":"50065","language":[{"iso":"eng"}]},{"author":[{"full_name":"Pei, Qiangyu","last_name":"Pei","first_name":"Qiangyu"},{"first_name":"Lin","last_name":"Wang","full_name":"Wang, Lin","id":"102868"},{"full_name":"Zhang, Dong","last_name":"Zhang","first_name":"Dong"},{"first_name":"Bingheng","full_name":"Yan, Bingheng","last_name":"Yan"},{"full_name":"Yu, Chen","last_name":"Yu","first_name":"Chen"},{"last_name":"Liu","full_name":"Liu, Fangming","first_name":"Fangming"}],"date_created":"2024-10-20T15:48:58Z","date_updated":"2024-10-20T15:49:03Z","conference":{"end_date":"2024-11-22","location":"Redmond","name":"ACM Symposium on Cloud Computing (SoCC)","start_date":"2024-11-20"},"title":"InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment","citation":{"chicago":"Pei, Qiangyu, Lin Wang, Dong Zhang, Bingheng Yan, Chen Yu, and Fangming Liu. “InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment.” In <i>Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)</i>, 2024.","ieee":"Q. Pei, L. Wang, D. Zhang, B. Yan, C. Yu, and F. Liu, “InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment,” presented at the ACM Symposium on Cloud Computing (SoCC), Redmond, 2024.","ama":"Pei Q, Wang L, Zhang D, Yan B, Yu C, Liu F. InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment. In: <i>Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)</i>. ; 2024.","apa":"Pei, Q., Wang, L., Zhang, D., Yan, B., Yu, C., &#38; Liu, F. (2024). InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment. <i>Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)</i>. ACM Symposium on Cloud Computing (SoCC), Redmond.","short":"Q. Pei, L. Wang, D. Zhang, B. Yan, C. Yu, F. Liu, in: Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC), 2024.","mla":"Pei, Qiangyu, et al. “InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment.” <i>Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)</i>, 2024.","bibtex":"@inproceedings{Pei_Wang_Zhang_Yan_Yu_Liu_2024, title={InferCool: Enhancing AI Inference Cooling through Transparent, Non-Intrusive Task Reassignment}, booktitle={Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)}, author={Pei, Qiangyu and Wang, Lin and Zhang, Dong and Yan, Bingheng and Yu, Chen and Liu, Fangming}, year={2024} }"},"year":"2024","user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"_id":"56689","language":[{"iso":"eng"}],"type":"conference","publication":"Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC)","status":"public"},{"issue":"2","publication_status":"published","publication_identifier":{"issn":["0922-6443","1573-1383"]},"citation":{"ama":"Nigade V, Bauszat P, Bal H, Wang L. Inference serving with end-to-end latency SLOs over dynamic edge networks. <i>Real-Time Systems</i>. 2024;60(2):239-290. doi:<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>","chicago":"Nigade, Vinod, Pablo Bauszat, Henri Bal, and Lin Wang. “Inference Serving with End-to-End Latency SLOs over Dynamic Edge Networks.” <i>Real-Time Systems</i> 60, no. 2 (2024): 239–90. <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">https://doi.org/10.1007/s11241-024-09418-4</a>.","ieee":"V. Nigade, P. Bauszat, H. Bal, and L. Wang, “Inference serving with end-to-end latency SLOs over dynamic edge networks,” <i>Real-Time Systems</i>, vol. 60, no. 2, pp. 239–290, 2024, doi: <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>.","apa":"Nigade, V., Bauszat, P., Bal, H., &#38; Wang, L. (2024). Inference serving with end-to-end latency SLOs over dynamic edge networks. <i>Real-Time Systems</i>, <i>60</i>(2), 239–290. <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">https://doi.org/10.1007/s11241-024-09418-4</a>","mla":"Nigade, Vinod, et al. “Inference Serving with End-to-End Latency SLOs over Dynamic Edge Networks.” <i>Real-Time Systems</i>, vol. 60, no. 2, Springer Science and Business Media LLC, 2024, pp. 239–90, doi:<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>.","bibtex":"@article{Nigade_Bauszat_Bal_Wang_2024, title={Inference serving with end-to-end latency SLOs over dynamic edge networks}, volume={60}, DOI={<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>}, number={2}, journal={Real-Time Systems}, publisher={Springer Science and Business Media LLC}, author={Nigade, Vinod and Bauszat, Pablo and Bal, Henri and Wang, Lin}, year={2024}, pages={239–290} }","short":"V. Nigade, P. Bauszat, H. Bal, L. Wang, Real-Time Systems 60 (2024) 239–290."},"intvolume":"        60","page":"239-290","year":"2024","date_created":"2025-12-12T08:16:33Z","author":[{"full_name":"Nigade, Vinod","last_name":"Nigade","first_name":"Vinod"},{"first_name":"Pablo","full_name":"Bauszat, Pablo","last_name":"Bauszat"},{"last_name":"Bal","full_name":"Bal, Henri","first_name":"Henri"},{"first_name":"Lin","id":"102868","full_name":"Wang, Lin","orcid":"0000-0001-7181-6128","last_name":"Wang"}],"volume":60,"publisher":"Springer Science and Business Media LLC","date_updated":"2025-12-12T08:18:05Z","doi":"10.1007/s11241-024-09418-4","title":"Inference serving with end-to-end latency SLOs over dynamic edge networks","type":"journal_article","publication":"Real-Time Systems","status":"public","abstract":[{"lang":"eng","text":"<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.\r\n</jats:p>"}],"user_id":"102868","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"_id":"63059","language":[{"iso":"eng"}]}]