{"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/silu","slug":"silu","name":"SiLU","full_name":"Sigmoid Linear Unit","full_name_withheld":false,"description_markdown":"** Sigmoid Linear Units**, or **SiLUs**, are activation functions for\r\nneural networks. The activation of the SiLU is computed by the sigmoid function multiplied by its input, or $$ x\\sigma(x).$$\r\n\r\nSee [Gaussian Error Linear Units](https://arxiv.org/abs/1606.08415) ([GELUs](https://paperswithcode.com/method/gelu)) where the SiLU was originally coined, and see [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://arxiv.org/abs/1702.03118) and [Swish: a Self-Gated Activation Function](https://arxiv.org/abs/1710.05941v1) where the SiLU was experimented with later.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","paper":"/paper/sigmoid-weighted-linear-units-for-neural","first_author":"Stefan Elfwing","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/sigmoid-weighted-linear-units-for-neural"},"source":{"url":"http://arxiv.org/abs/1702.03118v3","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/hendrycks/GELUs/blob/master/twitter_pos.py#L178","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Activation Functions","url":"/methods/category/activation-functions","pwc_aliases":[]}],"n_papers_tagged":30,"archive_num_papers":30,"papers_newest_first":[{"paper":"/paper/mvnet-hyperspectral-remote-sensing-image","slug":"mvnet-hyperspectral-remote-sensing-image","title":"MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture","date":"2025-07-06","arxiv_id":"2507.04409","n_code_links":1,"syntology":null},{"paper":"/paper/deriving-activation-functions-via-integration","slug":"deriving-activation-functions-via-integration","title":"Deriving Activation Functions Using Integration","date":"2024-11-20","arxiv_id":"2411.13010","n_code_links":1,"syntology":null},{"paper":"/paper/sparsing-law-towards-large-language-models","slug":"sparsing-law-towards-large-language-models","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","date":"2024-11-04","arxiv_id":"2411.02335","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp/SparsingLaw"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"actnas-generating-efficient-yolo-models-using","title":"ActNAS : Generating Efficient YOLO Models using Activation NAS","date":"2024-10-11","arxiv_id":"2410.10887","n_code_links":0,"syntology":null},{"paper":"/paper/unsegarmanet-unsupervised-image-segmentation","slug":"unsegarmanet-unsupervised-image-segmentation","title":"UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters","date":"2024-10-08","arxiv_id":"2410.06114","n_code_links":1,"syntology":null},{"paper":null,"slug":"braintransformers-snn-llm","title":"BrainTransformers: SNN-LLM","date":"2024-10-03","arxiv_id":"2410.14687","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-privacy-preserving-kan-inference","title":"Efficient Privacy-Preserving KAN Inference Using Homomorphic Encryption","date":"2024-09-12","arxiv_id":"2409.07751","n_code_links":0,"syntology":null},{"paper":null,"slug":"cipherdm-secure-three-party-inference-for","title":"CipherDM: Secure Three-Party Inference for Diffusion Model Sampling","date":"2024-09-09","arxiv_id":"2409.05414","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-expressive-power-of-quantized-neural","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","date":"2024-08-30","arxiv_id":"2409.00297","n_code_links":0,"syntology":null},{"paper":"/paper/reducing-fine-tuning-memory-overhead-by","slug":"reducing-fine-tuning-memory-overhead-by","title":"Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation","date":"2024-06-24","arxiv_id":"2406.16282","n_code_links":1,"syntology":{"ran":10,"of":21,"n_ran_checked":8,"n_instrument":2,"unverified":11,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 8 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","official":{"repos":["yyyyychen/LowMemoryBP"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"expanded-gating-ranges-improve-activation","title":"Expanded Gating Ranges Improve Activation Functions","date":"2024-05-25","arxiv_id":"2405.20768","n_code_links":0,"syntology":null},{"paper":null,"slug":"stable-and-robust-deep-learning-by-hyperbolic","title":"Stable and Robust Deep Learning By Hyperbolic Tangent Exponential Linear Unit (TeLU)","date":"2024-02-05","arxiv_id":"2402.02790","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-continuously-differentiable","slug":"leveraging-continuously-differentiable","title":"Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments","date":"2024-02-04","arxiv_id":"2402.02593","n_code_links":1,"syntology":null},{"paper":"/paper/relu-strikes-back-exploiting-activation","slug":"relu-strikes-back-exploiting-activation","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","date":"2023-10-06","arxiv_id":"2310.04564","n_code_links":1,"syntology":null},{"paper":"/paper/learnable-extended-activation-function-leaf","slug":"learnable-extended-activation-function-leaf","title":"Learnable Extended Activation Function (LEAF) for Deep Neural Networks","date":"2023-09-30","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"attention-only-transformers-and-implementing","title":"Attention-Only Transformers and Implementing MLPs with Attention Heads","date":"2023-09-15","arxiv_id":"2309.08593","n_code_links":0,"syntology":null},{"paper":"/paper/compact-approximating-complex-activation","slug":"compact-approximating-complex-activation","title":"Compact: Approximating Complex Activation Functions for Secure Computation","date":"2023-09-09","arxiv_id":"2309.04664","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-contract-design-via-discontinuous","title":"Deep Contract Design via Discontinuous Networks","date":"2023-07-05","arxiv_id":"2307.02318","n_code_links":0,"syntology":null},{"paper":null,"slug":"demystifying-oversmoothing-in-attention-based","title":"Demystifying Oversmoothing in Attention-Based Graph Neural Networks","date":"2023-05-25","arxiv_id":"2305.16102","n_code_links":0,"syntology":null},{"paper":null,"slug":"saturated-non-monotonic-activation-functions","title":"Saturated Non-Monotonic Activation Functions","date":"2023-05-12","arxiv_id":"2305.07537","n_code_links":0,"syntology":null},{"paper":"/paper/trainable-activations-for-image","slug":"trainable-activations-for-image","title":"Trainable Activations for Image Classification","date":"2023-01-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"optimizing-anchor-based-detectors-for","title":"Optimizing Anchor-based Detectors for Autonomous Driving Scenes","date":"2022-08-11","arxiv_id":"2208.06062","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-hybrid-activation-function-for-deep","slug":"adaptive-hybrid-activation-function-for-deep","title":"Adaptive hybrid activation function for deep neural networks","date":"2022-04-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-and-constructive-framework-for-the","title":"A Unified and Constructive Framework for the Universality of Neural Networks","date":"2021-12-30","arxiv_id":"2112.14877","n_code_links":0,"syntology":null},{"paper":"/paper/agglio-global-optimization-for-locally-convex","slug":"agglio-global-optimization-for-locally-convex","title":"AGGLIO: Global Optimization for Locally Convex Functions","date":"2021-11-06","arxiv_id":"2111.03932","n_code_links":1,"syntology":null},{"paper":"/paper/simple-training-strategies-and-model-scaling","slug":"simple-training-strategies-and-model-scaling","title":"Simple Training Strategies and Model Scaling for Object Detection","date":"2021-06-30","arxiv_id":"2107.00057","n_code_links":1,"syntology":null},{"paper":"/paper/low-curvature-activations-reduce-overfitting","slug":"low-curvature-activations-reduce-overfitting","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","date":"2021-02-15","arxiv_id":"2102.07861","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vasusingla/low_curvature_activations"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/bottleneck-transformers-for-visual","slug":"bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","n_code_links":13,"syntology":{"ran":26,"of":49,"n_ran_checked":19,"n_instrument":7,"unverified":23,"pointer_only":8,"phrase":"26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified","official":null}},{"paper":"/paper/searching-for-activation-functions","slug":"searching-for-activation-functions","title":"Searching for Activation Functions","date":"2017-10-16","arxiv_id":"1710.05941","n_code_links":22,"syntology":{"ran":13,"of":20,"n_ran_checked":8,"n_instrument":5,"unverified":7,"pointer_only":4,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/sigmoid-weighted-linear-units-for-neural","slug":"sigmoid-weighted-linear-units-for-neural","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","date":"2017-02-10","arxiv_id":"1702.03118","n_code_links":0,"syntology":null}],"papers_shown":30,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":30,"with_a_code_link":16,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":30,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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":5,"papers_where_code_ran_first_page":"/method/silu/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/silu/papers/ran/1","json":"/method/silu/papers/ran/1.json","rows":5}],"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":8},{"task":"/task/image-classification","name":"image-classification","papers":7},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":3},{"task":"/task/activation-function-synthesis","name":"Activation Function Synthesis","papers":2},{"task":null,"name":"GPU","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/learning-theory","name":"Learning Theory","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/privacy-preserving","name":"Privacy Preserving","papers":2},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/arc","name":"ARC","papers":1},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1}],"tasks_shown":20,"n_tasks":41,"usage_by_year":[{"year":"2017","papers":2},{"year":"2021","papers":5},{"year":"2022","papers":2},{"year":"2023","papers":8},{"year":"2024","papers":12},{"year":"2025","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/silu"},"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=SiLU","read_at":"2026-10-05T01:02:00+00:00","query":"SiLU","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":"1702.03118","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 'SiLU' -- 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":"e2ed83aa36e7a208da1bbeae0df34838de17af46d9adcaa62f5008846a7ce319","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}