{"url":"/method/realformer","slug":"realformer","name":"RealFormer","full_name":"RealFormer","full_name_withheld":false,"description_markdown":"**RealFormer** is a type of [Transformer](https://paperswithcode.com/methods/category/transformers) based on the idea of [residual](https://paperswithcode.com/method/residual-connection) attention. It adds skip edges to the backbone [Transformer](https://paperswithcode.com/method/transformer) to create multiple direct paths, one for each type of attention module. It adds no parameters or hyper-parameters. Specifically, RealFormer uses a Post-[LN](https://paperswithcode.com/method/layer-normalization) style Transformer as backbone and adds skip edges to connect [Multi-Head Attention](https://paperswithcode.com/method/multi-head-attention) modules in adjacent layers.","description_state":"present","introduced_year":null,"introduced_by":{"title":"RealFormer: Transformer Likes Residual Attention","paper":"/paper/informer-transformer-likes-informed-attention","first_author":"Ruining He","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/informer-transformer-likes-informed-attention"},"source":{"url":"https://arxiv.org/abs/2012.11747v3","title":"RealFormer: Transformer Likes Residual Attention","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":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/informer-transformer-likes-informed-attention","title":"RealFormer: Transformer Likes Residual Attention","date":"2020-12-21","arxiv_id":"2012.11747","n_code_links":5,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/linguistic-acceptability","name":"Linguistic Acceptability","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/natural-questions","name":"Natural Questions","papers":1},{"task":"/task/paraphrase-identification","name":"Paraphrase Identification","papers":1},{"task":"/task/semantic-textual-similarity","name":"Semantic Textual Similarity","papers":1},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":1},{"task":"/task/translation","name":"Translation","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2020","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/realformer"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}