{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:00:26Z","timestamp":1778256026772,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":152,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T00:00:00Z","timestamp":1716940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["61921003"],"award-info":[{"award-number":["61921003"]}]},{"name":"NSFC","award":["62102045"],"award-info":[{"award-number":["62102045"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,29]]},"DOI":"10.1145\/3636534.3649361","type":"proceedings-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T13:32:55Z","timestamp":1716989575000},"page":"279-295","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Mobile Foundation Model as Firmware"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2141-1496","authenticated-orcid":false,"given":"Jinliang","family":"Yuan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4932-8766","authenticated-orcid":false,"given":"Chen","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2751-2500","authenticated-orcid":false,"given":"Dongqi","family":"Cai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6883-2036","authenticated-orcid":false,"given":"Shihe","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5372-2168","authenticated-orcid":false,"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3583-5269","authenticated-orcid":false,"given":"Zeling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5932-8258","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2270-7071","authenticated-orcid":false,"given":"Dingge","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1195-1571","authenticated-orcid":false,"given":"Hanzi","family":"Mei","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-2936","authenticated-orcid":false,"given":"Xianqing","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7245-1298","authenticated-orcid":false,"given":"Shangguang","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6271-6993","authenticated-orcid":false,"given":"Mengwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Audio classification task. https:\/\/github.com\/mohaimenz\/acdnet."},{"key":"e_1_3_2_1_2_1","unstructured":"Gender recognition task. https:\/\/github.com\/wildchlamydia\/mivolo."},{"key":"e_1_3_2_1_3_1","unstructured":"Spoken language understanding task2. https:\/\/drive.google.com\/drive\/folders\/103t4_zqBZNqa_gGlIfteIs8_mdKhn3Rd?usp=sharing."},{"key":"e_1_3_2_1_4_1","unstructured":"Styler transfer task. https:\/\/github.com\/rinongal\/StyleGAN-nada."},{"key":"e_1_3_2_1_5_1","unstructured":"Text summary task. https:\/\/huggingface.co\/facebook\/bart-large-cnn."},{"key":"e_1_3_2_1_6_1","unstructured":"Vehicle re-identification task. https:\/\/github.com\/vimar-gu\/msinet."},{"key":"e_1_3_2_1_7_1","volume-title":"https:\/\/github.com\/maxy0524\/image_captioning\/tree\/master","author":"Image","year":"2015","unstructured":"Image captioning task. https:\/\/github.com\/maxy0524\/image_captioning\/tree\/master, 2015."},{"key":"e_1_3_2_1_8_1","volume-title":"https:\/\/github.com\/ppriyank\/MicronNet","author":"Traffic","year":"2018","unstructured":"Traffic sign classification task. https:\/\/github.com\/ppriyank\/MicronNet, 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"https:\/\/www.technologyreview.com\/2019\/12\/11\/131629\/apple-ai-personalizes-siri-federated-learning\/","author":"How","year":"2019","unstructured":"How apple personalizes siri without hoovering up your data. https:\/\/www.technologyreview.com\/2019\/12\/11\/131629\/apple-ai-personalizes-siri-federated-learning\/, 2019."},{"key":"e_1_3_2_1_10_1","volume-title":"https:\/\/github.com\/lukewys\/dcase_2020_T6\/tree\/master","author":"Audio","year":"2020","unstructured":"Audio captioning task. https:\/\/github.com\/lukewys\/dcase_2020_T6\/tree\/master, 2020."},{"key":"e_1_3_2_1_11_1","volume-title":"https:\/\/github.com\/descriptinc\/lyrebird-wav2clip","year":"2020","unstructured":"Audio\/text-to-image generation task. https:\/\/github.com\/descriptinc\/lyrebird-wav2clip, 2020."},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/github.com\/val-iisc\/css-ccnn","author":"Crowd","year":"2020","unstructured":"Crowd counting task. https:\/\/github.com\/val-iisc\/css-ccnn, 2020."},{"key":"e_1_3_2_1_13_1","volume-title":"https:\/\/github.com\/facebookresearch\/fairseq\/tree\/main\/examples\/wav2vec","year":"2020","unstructured":"Text-to-speech task. https:\/\/github.com\/facebookresearch\/fairseq\/tree\/main\/examples\/wav2vec, 2020."},{"key":"e_1_3_2_1_14_1","volume-title":"https:\/\/huggingface.co\/speechbrain\/asr-crdnn-rnnlm-librispeech\/tree\/main","author":"Automatic","year":"2021","unstructured":"Automatic speech recognition task. https:\/\/huggingface.co\/speechbrain\/asr-crdnn-rnnlm-librispeech\/tree\/main, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/drive.google.com\/drive\/folders\/1U9SiO4KkCNBKfxilXzJqBZ_k-vHz4ltV?usp=sharing","author":"Emotion","year":"2021","unstructured":"Emotion recognition task. https:\/\/drive.google.com\/drive\/folders\/1U9SiO4KkCNBKfxilXzJqBZ_k-vHz4ltV?usp=sharing, 2021."},{"key":"e_1_3_2_1_16_1","volume-title":"https:\/\/github.com\/dapowan\/LIMUBERT-Public","author":"Human","year":"2021","unstructured":"Human activity recognition task. https:\/\/github.com\/dapowan\/LIMUBERT-Public, 2021."},{"key":"e_1_3_2_1_17_1","volume-title":"https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/examples\/speech_commands","author":"Keyword","year":"2021","unstructured":"Keyword spotting task. https:\/\/github.com\/tensorflow\/tensorflow\/tree\/master\/tensorflow\/examples\/speech_commands, 2021."},{"key":"e_1_3_2_1_18_1","volume-title":"https:\/\/github.com\/speechbrain\/speechbrain\/tree\/develop\/recipes\/fluent-speech-commands","author":"Spoken","year":"2021","unstructured":"Spoken language understanding task1. https:\/\/github.com\/speechbrain\/speechbrain\/tree\/develop\/recipes\/fluent-speech-commands, 2021."},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmagic\/tree\/main\/configs\/real_esrgan","author":"Super","year":"2021","unstructured":"Super resolution task. https:\/\/github.com\/open-mmlab\/mmagic\/tree\/main\/configs\/real_esrgan, 2021."},{"key":"e_1_3_2_1_20_1","volume-title":"https:\/\/huggingface.co\/Salesforce\/codet5-base-multi-sum","author":"Code","year":"2022","unstructured":"Code document generation task. https:\/\/huggingface.co\/Salesforce\/codet5-base-multi-sum, 2022."},{"key":"e_1_3_2_1_21_1","volume-title":"https:\/\/huggingface.co\/microsoft\/codebertbase","author":"Code","year":"2022","unstructured":"Code generation task. https:\/\/huggingface.co\/microsoft\/codebertbase, 2022."},{"key":"e_1_3_2_1_22_1","volume-title":"https:\/\/huggingface.co\/cardiffnlp\/twitter-roberta-base-emoji","author":"Emoji","year":"2022","unstructured":"Emoji prediction task. https:\/\/huggingface.co\/cardiffnlp\/twitter-roberta-base-emoji, 2022."},{"key":"e_1_3_2_1_23_1","volume-title":"https:\/\/github.com\/friedrichor\/Language-Model-Next-Word-Prediction\/tree\/main","author":"Input","year":"2022","unstructured":"Input word prediction task. https:\/\/github.com\/friedrichor\/Language-Model-Next-Word-Prediction\/tree\/main, 2022."},{"key":"e_1_3_2_1_24_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmdetection\/tree\/main\/configs\/libra_rcnn","author":"Object","year":"2022","unstructured":"Object detection task1. https:\/\/github.com\/open-mmlab\/mmdetection\/tree\/main\/configs\/libra_rcnn, 2022."},{"key":"e_1_3_2_1_25_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmsegmentation\/tree\/main\/configs\/deeplabv3plus","author":"Semantic","year":"2022","unstructured":"Semantic segmentation task1. https:\/\/github.com\/open-mmlab\/mmsegmentation\/tree\/main\/configs\/deeplabv3plus, 2022."},{"key":"e_1_3_2_1_26_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmsegmentation\/tree\/main\/configs\/deeplabv3plus","author":"Semantic","year":"2022","unstructured":"Semantic segmentation task2. https:\/\/github.com\/open-mmlab\/mmsegmentation\/tree\/main\/configs\/deeplabv3plus, 2022."},{"key":"e_1_3_2_1_27_1","volume-title":"https:\/\/huggingface.co\/cardiffnlp\/twitter-roberta-base-sentiment-latest","author":"Sentiment","year":"2022","unstructured":"Sentiment analysis task. https:\/\/huggingface.co\/cardiffnlp\/twitter-roberta-base-sentiment-latest, 2022."},{"key":"e_1_3_2_1_28_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmaction2\/tree\/main\/configs\/recognition\/slowfast","author":"Video","year":"2022","unstructured":"Video classification task. https:\/\/github.com\/open-mmlab\/mmaction2\/tree\/main\/configs\/recognition\/slowfast, 2022."},{"key":"e_1_3_2_1_29_1","volume-title":"https:\/\/huggingface.co\/SamLowe\/roberta-base-go_emotions","author":"Emotion","year":"2023","unstructured":"Emotion prediction task. https:\/\/huggingface.co\/SamLowe\/roberta-base-go_emotions, 2023."},{"key":"e_1_3_2_1_30_1","volume-title":"https:\/\/huggingface.co\/pszemraj\/flan-t5-large-grammar-synthesis","author":"Grammatical","year":"2023","unstructured":"Grammatical error correction task. https:\/\/huggingface.co\/pszemraj\/flan-t5-large-grammar-synthesis, 2023."},{"key":"e_1_3_2_1_31_1","volume-title":"https:\/\/github.com\/open-mmlab\/mmpretrain\/tree\/main\/configs\/arcface","author":"Image","year":"2023","unstructured":"Image retrieval task. https:\/\/github.com\/open-mmlab\/mmpretrain\/tree\/main\/configs\/arcface, 2023."},{"key":"e_1_3_2_1_32_1","volume-title":"https:\/\/github.com\/huggingface\/transformers","author":"Machine","year":"2023","unstructured":"Machine translation task. https:\/\/github.com\/huggingface\/transformers, 2023."},{"key":"e_1_3_2_1_33_1","volume-title":"https:\/\/github.com\/yoctta\/xpaste","author":"Object","year":"2023","unstructured":"Object detection task2. https:\/\/github.com\/yoctta\/xpaste, 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"location recognition, and text-to-image retrieval task. https:\/\/github.com\/mlfoundations\/open_clip\/","author":"Optical","year":"2023","unstructured":"Optical character recognition, location recognition, and text-to-image retrieval task. https:\/\/github.com\/mlfoundations\/open_clip\/, 2023."},{"key":"e_1_3_2_1_35_1","volume-title":"https:\/\/huggingface.co\/deepset\/roberta-base-squad2","author":"Question","year":"2023","unstructured":"Question answering task1. https:\/\/huggingface.co\/deepset\/roberta-base-squad2, 2023."},{"key":"e_1_3_2_1_36_1","volume-title":"https:\/\/huggingface.co\/aubmindlab\/araelectra-base-discriminator","author":"Question","year":"2023","unstructured":"Question answering task2. https:\/\/huggingface.co\/aubmindlab\/araelectra-base-discriminator, 2023."},{"key":"e_1_3_2_1_37_1","volume-title":"https:\/\/huggingface.co\/JiaqiLee\/bert-agnews","author":"Text","year":"2023","unstructured":"Text classification task1. https:\/\/huggingface.co\/JiaqiLee\/bert-agnews, 2023."},{"key":"e_1_3_2_1_38_1","volume-title":"https:\/\/huggingface.co\/distilbert-base-uncased-finetuned-sst-2-english","author":"Text","year":"2023","unstructured":"Text classification task2. https:\/\/huggingface.co\/distilbert-base-uncased-finetuned-sst-2-english, 2023."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487863"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"e_1_3_2_1_42_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877--1901","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877--1901, 2020."},{"key":"e_1_3_2_1_43_1","volume-title":"Felix Xiaozhu Lin, and Mengwei Xu. Fedadapter: Efficient federated learning for modern nlp. arXiv preprint arXiv:2205.10162","author":"Cai Dongqi","year":"2022","unstructured":"Dongqi Cai, Yaozong Wu, Shangguang Wang, Felix Xiaozhu Lin, and Mengwei Xu. Fedadapter: Efficient federated learning for modern nlp. arXiv preprint arXiv:2205.10162, 2022."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307334.3326071"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"e_1_3_2_1_46_1","first-page":"5270","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen Yinpeng","year":"2022","unstructured":"Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Xiaoyi Dong, Lu Yuan, and Zicheng Liu. Mobile-former: Bridging mobilenet and transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 5270--5279, 2022."},{"key":"e_1_3_2_1_47_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311, 2022."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00850"},{"key":"e_1_3_2_1_49_1","first-page":"183","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Cui Weihao","year":"2022","unstructured":"Weihao Cui, Han Zhao, Quan Chen, Hao Wei, Zirui Li, Deze Zeng, Chao Li, and Minyi Guo. {DVABatch}: Diversity-aware {Multi-Entry}{Multi-Exit} batching for efficient processing of {DNN} services on {GPUs}. In 2022 USENIX Annual Technical Conference (USENIX ATC 22), pages 183--198, 2022."},{"key":"e_1_3_2_1_50_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_51_1","volume-title":"Xiaoli Li, and Cuntai Guan. Time-series representation learning via temporal and contextual contrasting. arXiv preprint arXiv:2106.14112","author":"Eldele Emadeldeen","year":"2021","unstructured":"Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. Time-series representation learning via temporal and contextual contrasting. arXiv preprint arXiv:2106.14112, 2021."},{"key":"e_1_3_2_1_52_1","first-page":"160","volume-title":"IFIP International Conference on Testing Software and Systems","author":"Abyane Amin Eslami","year":"2021","unstructured":"Amin Eslami Abyane and Hadi Hemmati. Robustness analysis of deep learning frameworks on mobile platforms. In IFIP International Conference on Testing Software and Systems, pages 160--177. Springer, 2021."},{"key":"e_1_3_2_1_53_1","volume-title":"Hugging face. https:\/\/huggingface.co\/","author":"Face Hugging","year":"2023","unstructured":"Hugging Face. Hugging face. https:\/\/huggingface.co\/, 2023."},{"key":"e_1_3_2_1_54_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323, 2022."},{"key":"e_1_3_2_1_55_1","first-page":"503","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Geoffrey X Yu","year":"2021","unstructured":"X Yu Geoffrey, Yubo Gao, Pavel Golikov, and Gennady Pekhimenko. Habitat: A {Runtime-Based} computational performance predictor for deep neural network training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21), pages 503--521, 2021."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2973750.2973777"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_58_1","unstructured":"github. github. https:\/\/github.com."},{"key":"e_1_3_2_1_59_1","volume-title":"Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778, 2021."},{"key":"e_1_3_2_1_60_1","volume-title":"Android neural networks api. https:\/\/github.com\/android\/ndk-samples\/tree\/main\/nn-samples","year":"2017","unstructured":"Google. Android neural networks api. https:\/\/github.com\/android\/ndk-samples\/tree\/main\/nn-samples, 2017."},{"key":"e_1_3_2_1_61_1","volume-title":"Aine Cahill, Stephen Shum, and Matthias Paulik. Improving on-device speaker verification using federated learning with privacy","author":"Granqvist Filip","year":"2020","unstructured":"Filip Granqvist, Matt Seigel, Rogier Van Dalen, Aine Cahill, Stephen Shum, and Matthias Paulik. Improving on-device speaker verification using federated learning with privacy. Proceedings of International Speech Communication Association, 2020."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173185"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_65_1","volume-title":"International Conference on Learning Representations","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_66_1","volume-title":"Qiang Liu, et al. Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045","author":"Huang Shaohan","year":"2023","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Qiang Liu, et al. Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045, 2023."},{"key":"e_1_3_2_1_67_1","volume-title":"Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991, 2015."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081360"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00119"},{"key":"e_1_3_2_1_70_1","volume-title":"jetson-stats. https:\/\/developer.nvidia.com\/embedded\/community\/jetson-projects\/jetson_stats","year":"2023","unstructured":"jetson stats. jetson-stats. https:\/\/developer.nvidia.com\/embedded\/community\/jetson-projects\/jetson_stats, 2023."},{"key":"e_1_3_2_1_71_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. Mistral 7b. arXiv preprint arXiv:2310.06825","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. Mistral 7b. arXiv preprint arXiv:2310.06825, 2023."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483274"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596853"},{"key":"e_1_3_2_1_75_1","volume-title":"Segment anything. arXiv preprint arXiv:2304.02643","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, et al. Segment anything. arXiv preprint arXiv:2304.02643, 2023."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596831"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2016.7460664"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470012"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02150"},{"key":"e_1_3_2_1_80_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, 34:9694--9705","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Caiming Xiong, and Steven Chu Hong Hoi. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, 34:9694--9705, 2021."},{"key":"e_1_3_2_1_81_1","volume-title":"Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv preprint arXiv:2310.08659","author":"Li Yixiao","year":"2023","unstructured":"Yixiao Li, Chen Liang, Pengcheng He, Nikos Karampatziakis, Weizhu Chen, and Tuo Zhao. Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv preprint arXiv:2310.08659, 2023."},{"key":"e_1_3_2_1_82_1","volume-title":"Personal llm agents: Insights and survey about the capability, efficiency and security. arXiv preprint arXiv:2401.05459","author":"Li Yuanchun","year":"2024","unstructured":"Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, et al. Personal llm agents: Insights and survey about the capability, efficiency and security. arXiv preprint arXiv:2401.05459, 2024."},{"key":"e_1_3_2_1_83_1","volume-title":"NeurIPS WS","author":"Lin Yujun","year":"2019","unstructured":"Yujun Lin, Driss Hafdi, Kuan Wang, Zhijian Liu, and Song Han. Neural-hardware architecture search. NeurIPS WS, 2019."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586250"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_2_1_87_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_2_1_89_1","volume-title":"Peft: State-of-the-art parameter-efficient fine-tuning methods. https:\/\/github.com\/huggingface\/peft","author":"Mangrulkar Sourab","year":"2022","unstructured":"Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, and Sayak Paul. Peft: State-of-the-art parameter-efficient fine-tuning methods. https:\/\/github.com\/huggingface\/peft, 2022."},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00020"},{"key":"e_1_3_2_1_91_1","volume-title":"Meta learning to bridge vision and language models for multimodal few-shot learning. arXiv preprint arXiv:2302.14794","author":"Najdenkoska Ivona","year":"2023","unstructured":"Ivona Najdenkoska, Xiantong Zhen, and Marcel Worring. Meta learning to bridge vision and language models for multimodal few-shot learning. arXiv preprint arXiv:2302.14794, 2023."},{"key":"e_1_3_2_1_92_1","volume-title":"Gpt-4 technical report. https:\/\/cdn.openai.com\/papers\/gpt-4.pdf","author":"AI.","year":"2023","unstructured":"OpenAI. Gpt-4 technical report. https:\/\/cdn.openai.com\/papers\/gpt-4.pdf, 2023."},{"key":"e_1_3_2_1_93_1","volume-title":"fairseq: A fast, extensible toolkit for sequence modeling. arXiv preprint arXiv:1904.01038","author":"Ott Myle","year":"2019","unstructured":"Myle Ott, Sergey Edunov, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. fairseq: A fast, extensible toolkit for sequence modeling. arXiv preprint arXiv:1904.01038, 2019."},{"key":"e_1_3_2_1_94_1","volume-title":"Paper with code. https:\/\/paperswithcode.com\/","year":"2023","unstructured":"paperswithcode. Paper with code. https:\/\/paperswithcode.com\/, 2023."},{"key":"e_1_3_2_1_95_1","volume-title":"Imagebind parameters. https:\/\/github.com\/facebookresearch\/ImageBind","author":"Imagebind","year":"2023","unstructured":"Imagebind parameters. Imagebind parameters. https:\/\/github.com\/facebookresearch\/ImageBind, 2023."},{"key":"e_1_3_2_1_96_1","volume-title":"Llama parameters. https:\/\/github.com\/facebookresearch\/llama","author":"LaMa","year":"2023","unstructured":"LLaMa parameters. Llama parameters. https:\/\/github.com\/facebookresearch\/llama, 2023."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596851"},{"key":"e_1_3_2_1_98_1","volume-title":"et al. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703, 2019."},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00033"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307334.3326098"},{"key":"e_1_3_2_1_101_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748--8763. PMLR, 2021."},{"key":"e_1_3_2_1_102_1","first-page":"28492","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, pages 28492--28518. PMLR, 2023."},{"key":"e_1_3_2_1_103_1","volume-title":"Global filter networks for image classification. Advances in neural information processing systems, 34:980--993","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, and Jie Zhou. Global filter networks for image classification. Advances in neural information processing systems, 34:980--993, 2021."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_105_1","volume-title":"Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100, 2022."},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483272"},{"key":"e_1_3_2_1_109_1","volume-title":"Eric Wallace, and Sameer Singh. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980","author":"Shin Taylor","year":"2020","unstructured":"Taylor Shin, Yasaman Razeghi, Robert L Logan IV, Eric Wallace, and Sameer Singh. Autoprompt: Eliciting knowledge from language models with automatically generated prompts. arXiv preprint arXiv:2010.15980, 2020."},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018885"},{"key":"e_1_3_2_1_111_1","volume-title":"Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. Pandagpt: One model to instruction-follow them all. arXiv preprint arXiv:2305.16355, 2023."},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01097"},{"key":"e_1_3_2_1_113_1","volume-title":"Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984","author":"Sun Zhiqing","year":"2020","unstructured":"Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, and Denny Zhou. Mobilebert: a compact task-agnostic bert for resource-limited devices. arXiv preprint arXiv:2004.02984, 2020."},{"key":"e_1_3_2_1_114_1","volume-title":"Any-to-any generation via composable diffusion. arXiv preprint arXiv:2305.11846","author":"Tang Zineng","year":"2023","unstructured":"Zineng Tang, Ziyi Yang, Chenguang Zhu, Michael Zeng, and Mohit Bansal. Any-to-any generation via composable diffusion. arXiv preprint arXiv:2305.11846, 2023."},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_116_1","volume-title":"Tflite tools. https:\/\/www.tensorflow.org\/lite\/performance\/measurement","author":"Lite","year":"2023","unstructured":"TFLite tools. Tflite tools. https:\/\/www.tensorflow.org\/lite\/performance\/measurement, 2023."},{"key":"e_1_3_2_1_117_1","volume-title":"et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023."},{"key":"e_1_3_2_1_118_1","volume-title":"Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023."},{"key":"e_1_3_2_1_119_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3418161"},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00057"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313611"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"e_1_3_2_1_125_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652, 2021."},{"key":"e_1_3_2_1_126_1","volume-title":"Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, et al. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771, 2019."},{"key":"e_1_3_2_1_127_1","volume-title":"Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519","author":"Wu Shengqiong","year":"2023","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. Next-gpt: Any-to-any multimodal llm. arXiv preprint arXiv:2309.05519, 2023."},{"key":"e_1_3_2_1_128_1","volume-title":"Optimization of operation strategy for primary torque based hydrostatic drivetrain using artificial intelligence. arXiv preprint arXiv:2003.10011","author":"Xiang Yusheng","year":"2020","unstructured":"Yusheng Xiang and Marcus Geimer. Optimization of operation strategy for primary torque based hydrostatic drivetrain using artificial intelligence. arXiv preprint arXiv:2003.10011, 2020."},{"key":"e_1_3_2_1_129_1","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. Imagereward: Learning and evaluating human preferences for text-to-image generation. arXiv preprint arXiv:2304.05977, 2023."},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313591"},{"key":"e_1_3_2_1_131_1","volume-title":"Federated fine-tuning of billion-sized language models across mobile devices. arXiv preprint arXiv:2308.13894","author":"Xu Mengwei","year":"2023","unstructured":"Mengwei Xu, Yaozong Wu, Dongqi Cai, Xiang Li, and Shangguang Wang. Federated fine-tuning of billion-sized language models across mobile devices. arXiv preprint arXiv:2308.13894, 2023."},{"key":"e_1_3_2_1_132_1","volume-title":"A survey of resource-efficient llm and multimodal foundation models. arXiv preprint arXiv:2401.08092","author":"Xu Mengwei","year":"2024","unstructured":"Mengwei Xu, Wangsong Yin, Dongqi Cai, Rongjie Yi, Daliang Xu, Qipeng Wang, Bingyang Wu, Yihao Zhao, Chen Yang, Shihe Wang, et al. A survey of resource-efficient llm and multimodal foundation models. arXiv preprint arXiv:2401.08092, 2024."},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"e_1_3_2_1_134_1","article-title":"Vision transformer for generic body pose estimation","author":"Xu Yufei","year":"2023","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. Vitpose++: Vision transformer for generic body pose estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_135_1","volume-title":"Beyond triangle inequality: Sifting noisy and outlier distance measurements for localization. ACM Transactions on Sensor Networks (TOSN), 9(2):1--20","author":"Yang Zheng","year":"2013","unstructured":"Zheng Yang, Lirong Jian, Chenshu Wu, and Yunhao Liu. Beyond triangle inequality: Sifting noisy and outlier distance measurements for localization. ACM Transactions on Sensor Networks (TOSN), 9(2):1--20, 2013."},{"key":"e_1_3_2_1_136_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228980"},{"key":"e_1_3_2_1_137_1","volume-title":"Edgemoe: Fast on-device inference of moe-based large language models. arXiv preprint arXiv:2308.14352","author":"Yi Rongjie","year":"2023","unstructured":"Rongjie Yi, Liwei Guo, Shiyun Wei, Ao Zhou, Shangguang Wang, and Mengwei Xu. Edgemoe: Fast on-device inference of moe-based large language models. arXiv preprint arXiv:2308.14352, 2023."},{"key":"e_1_3_2_1_138_1","volume-title":"A survey on multimodal large language models. arXiv preprint arXiv:2306.13549","author":"Yin Shukang","year":"2023","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549, 2023."},{"key":"e_1_3_2_1_139_1","first-page":"521","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. Orca: A distributed serving system for {Transformer-Based} generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 521--538, 2022."},{"key":"e_1_3_2_1_140_1","volume-title":"Model zoo. https:\/\/modelzoo.co\/","author":"Yu Koh Jing","year":"2023","unstructured":"Koh Jing Yu. Model zoo. https:\/\/modelzoo.co\/, 2023."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517016"},{"key":"e_1_3_2_1_142_1","volume-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199","author":"Zaken Elad Ben","year":"2021","unstructured":"Elad Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199, 2021."},{"key":"e_1_3_2_1_143_1","volume-title":"Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414","author":"Zeng Aohan","year":"2022","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et al. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414, 2022."},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512148"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00072"},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467886"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071077"},{"key":"e_1_3_2_1_150_1","first-page":"18330","article-title":"Bert loses patience: Fast and robust inference with early exit","volume":"33","author":"Zhou Wangchunshu","year":"2020","unstructured":"Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei. Bert loses patience: Fast and robust inference with early exit. Advances in Neural Information Processing Systems, 33:18330--18341, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"e_1_3_2_1_152_1","volume-title":"Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910","author":"Zhou Yongchao","year":"2022","unstructured":"Yongchao Zhou, Andrei Ioan Muresanu, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. Large language models are human-level prompt engineers. arXiv preprint arXiv:2211.01910, 2022."}],"event":{"name":"ACM MobiCom '24: 30th Annual International Conference on Mobile Computing and Networking","location":"Washington D.C. DC USA","acronym":"ACM MobiCom '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 30th Annual International Conference on Mobile Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3649361","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3636534.3649361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:54:12Z","timestamp":1750287252000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3649361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,29]]},"references-count":152,"alternative-id":["10.1145\/3636534.3649361","10.1145\/3636534"],"URL":"https:\/\/doi.org\/10.1145\/3636534.3649361","relation":{},"subject":[],"published":{"date-parts":[[2024,5,29]]},"assertion":[{"value":"2024-05-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}