{"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":"/task/dynamic-neural-networks","name":"Dynamic neural networks","slug":"dynamic-neural-networks","description_markdown":"Dynamic neural networks are adaptable models that can change their structure or parameters during training or inference based on input complexity or computational constraints. They offer benefits like improved efficiency, adaptability, and scalability compared to static architectures.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":37,"papers_with_code":15,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":37,"of":37,"of_with_code":15,"tagged_in_all":37,"counts":{"archive_papers_tagged":37,"with_a_code_link":15,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":37,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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"},"items":[{"url":"/paper/a-survey-on-dynamic-neural-networks-from","slug":"a-survey-on-dynamic-neural-networks-from","title":"A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion","date":"2025-01-13","arxiv_id":"2501.07451","repositories_listed":1,"syntology":null},{"url":"/paper/dyfadet-dynamic-feature-aggregation-for","slug":"dyfadet-dynamic-feature-aggregation-for","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","date":"2024-07-03","arxiv_id":"2407.03197","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dyfadet-dynamic-feature-aggregation-for#ran","syntology_url":"https://syntology.ai/paper/2407.03197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03197"}},"official":{"repos":["yangle15/DyFADet-pytorch"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-dnns-and-runtime-management-for","slug":"dynamic-dnns-and-runtime-management-for","title":"Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices","date":"2024-01-17","arxiv_id":"2401.08965","repositories_listed":1,"syntology":null},{"url":"/paper/jointly-learned-exit-and-inference-for-a","slug":"jointly-learned-exit-and-inference-for-a","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","date":"2023-10-13","arxiv_id":"2310.09163","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/jointly-learned-exit-and-inference-for-a#ran","syntology_url":"https://syntology.ai/paper/2310.09163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09163"}},"official":{"repos":["networkslab/dynn"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-neural-network-is-all-you-need","slug":"dynamic-neural-network-is-all-you-need","title":"Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks","date":"2023-08-17","arxiv_id":"2308.08709","repositories_listed":1,"syntology":null},{"url":"/paper/fixing-overconfidence-in-dynamic-neural","slug":"fixing-overconfidence-in-dynamic-neural","title":"Fixing Overconfidence in Dynamic Neural Networks","date":"2023-02-13","arxiv_id":"2302.06359","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/fixing-overconfidence-in-dynamic-neural#ran","syntology_url":"https://syntology.ai/paper/2302.06359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06359"}},"official":{"repos":["aaltoml/calibrated-dnn"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hadas-hardware-aware-dynamic-neural","slug":"hadas-hardware-aware-dynamic-neural","title":"HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling","date":"2022-12-06","arxiv_id":"2212.03354","repositories_listed":1,"syntology":null},{"url":"/paper/boosted-dynamic-neural-networks","slug":"boosted-dynamic-neural-networks","title":"Boosted Dynamic Neural Networks","date":"2022-11-30","arxiv_id":"2211.16726","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/boosted-dynamic-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2211.16726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16726"}},"official":{"repos":["SHI-Labs/Boosted-Dynamic-Networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/satbench-benchmarking-the-speed-accuracy","slug":"satbench-benchmarking-the-speed-accuracy","title":"SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks","date":"2022-06-16","arxiv_id":"2206.08427","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-domain-generalization-with-drift","slug":"temporal-domain-generalization-with-drift","title":"Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks","date":"2022-05-21","arxiv_id":"2205.10664","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/temporal-domain-generalization-with-drift#ran","syntology_url":"https://syntology.ai/paper/2205.10664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10664"}},"official":{"repos":["baithebest/drain"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dynashare-dynamic-neural-networks-for-multi","slug":"dynashare-dynamic-neural-networks-for-multi","title":"DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNING","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-task-oriented-communication-for-edge","slug":"learning-task-oriented-communication-for-edge","title":"Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach","date":"2021-02-08","arxiv_id":"2102.04170","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-dual-gating-neural-networks","slug":"dynamic-dual-gating-neural-networks","title":"Dynamic Dual Gating Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ampnet-asynchronous-model-parallel-training","slug":"ampnet-asynchronous-model-parallel-training","title":"AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks","date":"2017-05-27","arxiv_id":"1705.09786","repositories_listed":1,"syntology":null},{"url":"/paper/nonlinear-systems-identification-using-deep","slug":"nonlinear-systems-identification-using-deep","title":"Nonlinear Systems Identification Using Deep Dynamic Neural Networks","date":"2016-10-05","arxiv_id":"1610.01439","repositories_listed":1,"syntology":null},{"url":null,"slug":"parametric-taylor-series-based-latent","title":"Parametric Taylor series based latent dynamics identification neural networks","date":"2024-10-05","arxiv_id":"2410.04193","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-introduction-to-cognidynamics","title":"An Introduction to Cognidynamics","date":"2024-08-18","arxiv_id":"2408.13112","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuroevolving-electronic-dynamical-networks","title":"Neuroevolving Electronic Dynamical Networks","date":"2024-04-06","arxiv_id":"2404.04587","repositories_listed":0,"syntology":null},{"url":null,"slug":"subnetwork-to-go-elastic-neural-network-with","title":"Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference","date":"2023-12-06","arxiv_id":"2312.03464","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-distance-gesture-recognition-using","title":"Long-Distance Gesture Recognition using Dynamic Neural Networks","date":"2023-08-09","arxiv_id":"2308.04643","repositories_listed":0,"syntology":null},{"url":null,"slug":"monadic-deep-learning","title":"Monadic Deep Learning","date":"2023-07-23","arxiv_id":"2307.12187","repositories_listed":0,"syntology":null},{"url":null,"slug":"dycl-dynamic-neural-network-compilation-via","title":"DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization","date":"2023-07-11","arxiv_id":"2307.04963","repositories_listed":0,"syntology":null},{"url":null,"slug":"stock-price-prediction-using-dynamic-neural","title":"Stock Price Prediction using Dynamic Neural Networks","date":"2023-06-18","arxiv_id":"2306.12969","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-artificial-neural-networks-to","title":"Evolving Artificial Neural Networks To Imitate Human Behaviour In Shinobi III : Return of the Ninja Master","date":"2023-04-03","arxiv_id":"2304.01096","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradmdm-adversarial-attack-on-dynamic","title":"GradMDM: Adversarial Attack on Dynamic Networks","date":"2023-04-01","arxiv_id":"2304.06724","repositories_listed":0,"syntology":null},{"url":null,"slug":"ed-batch-efficient-automatic-batching-of","title":"ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines","date":"2023-02-08","arxiv_id":"2302.03851","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dark-side-of-dynamic-routing-neural","title":"The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-membership-inference-attack-against","title":"A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information","date":"2022-10-17","arxiv_id":"2210.08956","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-demand-resource-management-for-6g-wireless","title":"On-Demand Resource Management for 6G Wireless Networks Using Knowledge-Assisted Dynamic Neural Networks","date":"2022-08-02","arxiv_id":"2208.01785","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-dynamic-neural-networks-for","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","date":"2022-02-15","arxiv_id":"2202.07101","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedded-knowledge-distillation-in-depth","title":"Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network","date":"2021-03-01","arxiv_id":"2103.00793","repositories_listed":0,"syntology":null},{"url":null,"slug":"siamese-labels-auxiliary-network-silanet","title":"Siamese Labels Auxiliary Learning","date":"2021-02-27","arxiv_id":"2103.00200","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-neural-networks-a-survey","title":"Dynamic Neural Networks: A Survey","date":"2021-02-09","arxiv_id":"2102.04906","repositories_listed":0,"syntology":null},{"url":null,"slug":"nimble-efficiently-compiling-dynamic-neural","title":"Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference","date":"2020-06-04","arxiv_id":"2006.03031","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-dynamic-neural-networks-for","title":"Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison","date":"2019-05-30","arxiv_id":"1905.13268","repositories_listed":0,"syntology":null},{"url":null,"slug":"cavs-a-vertex-centric-programming-interface","title":"Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks","date":"2017-12-11","arxiv_id":"1712.04048","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-memory-organization-for-dynamic","title":"Analysis of Memory Organization for Dynamic Neural Networks","date":null,"arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/task/dynamic-neural-networks/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/dynamic-neural-networks/papers/ran/1","json":"/task/dynamic-neural-networks/papers/ran/1.json","rows":5}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"9e7bf691aaa1135ba56cac6d7f15930399fa28881c2c3a8079897260cbe93668","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}