{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/mobilebert","slug":"mobilebert","name":"MobileBERT","full_name":"MobileBERT","full_name_withheld":false,"description_markdown":"**MobileBERT** is a type of inverted-bottleneck [BERT](https://paperswithcode.com/method/bert) that compresses and accelerates the popular BERT model. MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. To train MobileBERT, we first train a specially designed teacher model, an inverted-bottleneck incorporated BERT_LARGE model. Then, we conduct knowledge transfer from this teacher to MobileBERT. Like the original BERT, MobileBERT is task-agnostic, that is, it can be generically applied to various downstream NLP tasks via simple fine-tuning. It is trained by layer-to-layer imitating the inverted bottleneck BERT.","description_state":"present","introduced_year":null,"introduced_by":{"title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","paper":"/paper/mobilebert-a-compact-task-agnostic-bert-for","first_author":"Zhiqing Sun","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mobilebert-a-compact-task-agnostic-bert-for"},"source":{"url":"https://arxiv.org/abs/2004.02984v2","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Autoencoding Transformers","url":"/methods/category/autoencoding-transformers","pwc_aliases":[]},{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":12,"archive_num_papers":12,"papers_newest_first":[{"paper":null,"slug":"efficient-intent-based-filtering-for-multi","title":"Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs","date":"2025-03-21","arxiv_id":"2503.17336","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedmentalcare-towards-privacy-preserving-fine","title":"FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework","date":"2025-02-27","arxiv_id":"2503.05786","n_code_links":0,"syntology":null},{"paper":null,"slug":"resource-efficient-transformer-architecture","title":"Resource-Efficient Transformer Architecture: Optimizing Memory and Execution Time for Real-Time Applications","date":"2024-12-25","arxiv_id":"2501.00042","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-deployment-of-transformer-models-in","slug":"efficient-deployment-of-transformer-models-in","title":"Efficient Deployment of Transformer Models in Analog In-Memory Computing Hardware","date":"2024-11-26","arxiv_id":"2411.17367","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-device-emoji-classifier-trained-with-gpt","title":"On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard","date":"2024-11-06","arxiv_id":"2411.05031","n_code_links":0,"syntology":null},{"paper":"/paper/utilizing-large-language-models-to-optimize","slug":"utilizing-large-language-models-to-optimize","title":"PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT","date":"2024-08-11","arxiv_id":"2408.05667","n_code_links":2,"syntology":null},{"paper":"/paper/toward-attention-based-tinyml-a-heterogeneous","slug":"toward-attention-based-tinyml-a-heterogeneous","title":"Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow","date":"2024-08-05","arxiv_id":"2408.02473","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantized-transformer-language-model","title":"Quantized Transformer Language Model Implementations on Edge Devices","date":"2023-10-06","arxiv_id":"2310.03971","n_code_links":0,"syntology":null},{"paper":null,"slug":"autodistill-an-end-to-end-framework-to","title":"AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models","date":"2022-01-21","arxiv_id":"2201.08539","n_code_links":0,"syntology":null},{"paper":"/paper/character-level-hypernetworks-for-hate-speech","slug":"character-level-hypernetworks-for-hate-speech","title":"Character-level HyperNetworks for Hate Speech Detection","date":"2021-11-11","arxiv_id":"2111.06336","n_code_links":1,"syntology":null},{"paper":"/paper/lidsnet-a-lightweight-on-device-intent","slug":"lidsnet-a-lightweight-on-device-intent","title":"LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network","date":"2021-10-06","arxiv_id":"2110.15717","n_code_links":0,"syntology":null},{"paper":"/paper/mobilebert-a-compact-task-agnostic-bert-for","slug":"mobilebert-a-compact-task-agnostic-bert-for","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","date":"2020-04-06","arxiv_id":"2004.02984","n_code_links":7,"syntology":null}],"papers_shown":12,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":12,"with_a_code_link":5,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/privacy-preserving","name":"Privacy Preserving","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/bayesian-optimization","name":"Bayesian Optimization","papers":1},{"task":"/task/federated-learning","name":"Federated Learning","papers":1},{"task":"/task/hate-speech-detection","name":"Hate Speech Detection","papers":1},{"task":"/task/intent-classification","name":"Intent Classification","papers":1},{"task":"/task/intent-detection","name":"Intent Detection","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/model-compression","name":"Model Compression","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1},{"task":"/task/phishing-website-detection","name":"Phishing Website Detection","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1}],"tasks_shown":20,"n_tasks":24,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":5},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mobilebert"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=MobileBERT","read_at":"2026-10-05T00:59:12+00:00","query":"MobileBERT","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"MobileBERT","origin_arxiv_id":"2004.02984"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2004.02984","repositories":{"listed":5,"in_graph":7,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2004.02984","citations":1076},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'MobileBERT'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2004.02984","page":"/paper/mobilebert-a-compact-task-agnostic-bert-for","syntology_url":"https://syntology.ai/paper/2004.02984","in_graph_layer":false,"samples":0},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 7 in the graph, strongest link: official). This answer is about arXiv:2004.02984, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"90e238d381aa7f4136acf89ecd263af4d124eea2cfa6f41126f581caa3f61af6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}