{"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/layerdrop","slug":"layerdrop","name":"LayerDrop","full_name":"LayerDrop","full_name_withheld":false,"description_markdown":"**LayerDrop** is a form of structured [dropout](https://paperswithcode.com/method/dropout) for [Transformer](https://paperswithcode.com/method/transformer) models which has a regularization effect during training and allows for efficient pruning at inference time. It randomly drops layers from the Transformer according to an \"every other\" strategy where pruning with a rate $p$ means dropping the layers at depth $d$ such that $d = 0\\left\\(\\text{mod}\\left(\\text{floor}\\left(\\frac{1}{p}\\right)\\right)\\right)$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Reducing Transformer Depth on Demand with Structured Dropout","paper":"/paper/reducing-transformer-depth-on-demand-with-1","first_author":"Angela Fan","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/reducing-transformer-depth-on-demand-with-1"},"source":{"url":"https://arxiv.org/abs/1909.11556v1","title":"Reducing Transformer Depth on Demand with Structured Dropout","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/fairseq/blob/9ebcd6554daab7bac4948de49aeb85bfff81d876/fairseq/checkpoint_utils.py#L365-L446","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/perceiver-vl-efficient-vision-and-language","slug":"perceiver-vl-efficient-vision-and-language","title":"Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention","date":"2022-11-21","arxiv_id":"2211.11701","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-flexible-depth-model-by-multi-task","title":"Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation","date":"2020-10-16","arxiv_id":"2010.08265","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-transformer-depth-on-demand-with-1","slug":"reducing-transformer-depth-on-demand-with-1","title":"Reducing Transformer Depth on Demand with Structured Dropout","date":"2019-09-25","arxiv_id":"1909.11556","n_code_links":5,"syntology":null}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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":1,"papers_where_code_ran_first_page":"/method/layerdrop/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/layerdrop/papers/ran/1","json":"/method/layerdrop/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/machine-translation","name":"Machine Translation","papers":2},{"task":"/task/translation","name":"Translation","papers":2},{"task":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval","papers":1},{"task":"/task/gsm8k","name":"GSM8K","papers":1},{"task":"/task/hellaswag","name":"HellaSwag","papers":1},{"task":"/task/humaneval","name":"HumanEval","papers":1},{"task":"/task/mmlu","name":"MMLU","papers":1},{"task":"/task/math","name":"Math","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/natural-questions","name":"Natural Questions","papers":1},{"task":"/task/open-domain-question-answering","name":"Open-Domain Question Answering","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/race-h","name":"RACE-h","papers":1},{"task":"/task/race-m","name":"RACE-m","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/triviaqa","name":"TriviaQA","papers":1},{"task":"/task/winogrande","name":"Winogrande","papers":1}],"tasks_shown":19,"n_tasks":19,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":1},{"year":"2022","papers":1},{"year":"2024","papers":1}],"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/layerdrop"},"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=LayerDrop","read_at":"2026-10-05T00:58:26+00:00","query":"LayerDrop","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1909.11556","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'LayerDrop' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"47e30e8eeaa568b710ee0d23a932f231c604055ba5277e367bfc22367a5e3b8d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}