{"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/adamw/papers/ran/1","list_of":"/method/adamw","method":"AdamW","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,43],"of":43,"counts":{"archive_papers_tagged":206,"with_a_code_link":114,"where_syntology_ran_a_sample":43,"not_listed_spam_title":0,"listed":206,"listed_where_code_ran":43,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":38,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":38,"listed_every_run_a_failure_of_syntologys_instrument":5,"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"},"first_page":"/method/adamw/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/adams-momentum-itself-can-be-a-normalizer-for","slug":"adams-momentum-itself-can-be-a-normalizer-for","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","date":"2025-05-22","arxiv_id":"2505.16363","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 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","official":{"repos":["pku-huzhang/AdamS"],"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":["found_in_text"]}}},{"paper":"/paper/accelerating-neural-network-training-an","slug":"accelerating-neural-network-training-an","title":"Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition","date":"2025-02-20","arxiv_id":"2502.15015","n_code_links":2,"syntology":{"ran":16,"of":19,"n_ran_checked":16,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/a-stronger-mixture-of-low-rank-experts-for","slug":"a-stronger-mixture-of-low-rank-experts-for","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","date":"2025-02-20","arxiv_id":"2502.15828","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["thudm/moelora_riemannian"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/apollo-sgd-like-memory-adamw-level","slug":"apollo-sgd-like-memory-adamw-level","title":"APOLLO: SGD-like Memory, AdamW-level Performance","date":"2024-12-06","arxiv_id":"2412.05270","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zhuhanqing/APOLLO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mars-unleashing-the-power-of-variance","slug":"mars-unleashing-the-power-of-variance","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","date":"2024-11-15","arxiv_id":"2411.10438","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["AGI-Arena/MARS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/variational-low-rank-adaptation-using-ivon","slug":"variational-low-rank-adaptation-using-ivon","title":"Variational Low-Rank Adaptation Using IVON","date":"2024-11-07","arxiv_id":"2411.04421","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["team-approx-bayes/ivon-lora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-weight-decay-for-robust-fine","slug":"rethinking-weight-decay-for-robust-fine","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","date":"2024-11-03","arxiv_id":"2411.01713","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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","official":{"repos":["gt-ripl/selective-projection-decay"],"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"]}}},{"paper":"/paper/the-accuracy-paradox-in-rlhf-when-better","slug":"the-accuracy-paradox-in-rlhf-when-better","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","date":"2024-10-09","arxiv_id":"2410.06554","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"5 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["EIT-NLP/AccuracyParadox-RLHF"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-much-can-we-forget-about-data","slug":"how-much-can-we-forget-about-data","title":"How Much Can We Forget about Data Contamination?","date":"2024-10-04","arxiv_id":"2410.03249","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tml-tuebingen/forgetting-contamination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-ademamix-optimizer-better-faster-older","slug":"the-ademamix-optimizer-better-faster-older","title":"The AdEMAMix Optimizer: Better, Faster, Older","date":"2024-09-05","arxiv_id":"2409.03137","n_code_links":4,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["apple/ml-ademamix"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/resolving-discrepancies-in-compute-optimal","slug":"resolving-discrepancies-in-compute-optimal","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","date":"2024-06-27","arxiv_id":"2406.19146","n_code_links":3,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 3 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["formll/resolving-scaling-law-discrepancies","formll/resolving-scaling-law-discrepencies"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/adam-mini-use-fewer-learning-rates-to-gain","slug":"adam-mini-use-fewer-learning-rates-to-gain","title":"Adam-mini: Use Fewer Learning Rates To Gain More","date":"2024-06-24","arxiv_id":"2406.16793","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zyushun/adam-mini"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/improving-generalization-and-convergence-by","slug":"improving-generalization-and-convergence-by","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","date":"2024-05-31","arxiv_id":"2405.20763","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wmz9/ire-algorithm-framework"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/accurate-and-well-calibrated-icd-code","slug":"accurate-and-well-calibrated-icd-code","title":"Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings","date":"2024-02-05","arxiv_id":"2402.03172","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["gecgomes/icd_coding_msam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/riemannian-preconditioned-lora-for-fine","slug":"riemannian-preconditioned-lora-for-fine","title":"Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models","date":"2024-02-04","arxiv_id":"2402.02347","n_code_links":1,"syntology":{"ran":15,"of":21,"n_ran_checked":11,"n_instrument":4,"unverified":6,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["pilancilab/Riemannian_Preconditioned_LoRA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/hift-a-hierarchical-full-parameter-fine","slug":"hift-a-hierarchical-full-parameter-fine","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","date":"2024-01-26","arxiv_id":"2401.15207","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["misonsky/HiFT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/structured-inverse-free-natural-gradient","slug":"structured-inverse-free-natural-gradient","title":"Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC","date":"2023-12-09","arxiv_id":"2312.05705","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 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","official":{"repos":["f-dangel/singd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/outcome-supervised-verifiers-for-planning-in","slug":"outcome-supervised-verifiers-for-planning-in","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","date":"2023-11-16","arxiv_id":"2311.09724","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-quadratic-synchronization-rule-for","slug":"a-quadratic-synchronization-rule-for","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","date":"2023-10-22","arxiv_id":"2310.14423","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hmgxr128/qsr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/adalomo-low-memory-optimization-with-adaptive","slug":"adalomo-low-memory-optimization-with-adaptive","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","date":"2023-10-16","arxiv_id":"2310.10195","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openlmlab/lomo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-enhanced-optimizers-for-structure-aware","slug":"graph-enhanced-optimizers-for-structure-aware","title":"Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution","date":"2023-09-24","arxiv_id":"2310.03032","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mtandhj/sevo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","n_code_links":19,"syntology":{"ran":33,"of":52,"n_ran_checked":22,"n_instrument":11,"unverified":19,"pointer_only":20,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 1 violated, 20 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/rotational-optimizers-simple-robust-dnn","slug":"rotational-optimizers-simple-robust-dnn","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","date":"2023-05-26","arxiv_id":"2305.17212","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["epfml/req","epfml/rotational-optimizers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-is-all-you-need-learning-language","slug":"text-is-all-you-need-learning-language","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","date":"2023-05-23","arxiv_id":"2305.13731","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":"/paper/unlimiformer-long-range-transformers-with","slug":"unlimiformer-long-range-transformers-with","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","date":"2023-05-02","arxiv_id":"2305.01625","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 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":["abertsch72/unlimiformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/customized-segment-anything-model-for-medical","slug":"customized-segment-anything-model-for-medical","title":"Customized Segment Anything Model for Medical Image Segmentation","date":"2023-04-26","arxiv_id":"2304.13785","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":3,"n_instrument":3,"unverified":3,"pointer_only":4,"phrase":"6 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hitachinsk/samed"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-stochastic-proximal-polyak-step-size","slug":"a-stochastic-proximal-polyak-step-size","title":"A Stochastic Proximal Polyak Step Size","date":"2023-01-12","arxiv_id":"2301.04935","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fabian-sp/ProxSPS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/amos-an-adam-style-optimizer-with-adaptive","slug":"amos-an-adam-style-optimizer-with-adaptive","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","date":"2022-10-21","arxiv_id":"2210.11693","n_code_links":1,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["google-research/jestimator"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-injected-prompt-based-fine-tuning","slug":"knowledge-injected-prompt-based-fine-tuning","title":"Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding","date":"2022-10-07","arxiv_id":"2210.03304","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["whaleloops/KEPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/nag-gs-semi-implicit-accelerated-and-robust","slug":"nag-gs-semi-implicit-accelerated-and-robust","title":"NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer","date":"2022-09-29","arxiv_id":"2209.14937","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["skolai/nag-gs","naggsopt/naggs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sequencer-deep-lstm-for-image-classification","slug":"sequencer-deep-lstm-for-image-classification","title":"Sequencer: Deep LSTM for Image Classification","date":"2022-05-04","arxiv_id":"2205.01972","n_code_links":5,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["okojoalg/sequencer","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-adamw-through-proximal-methods-1","slug":"understanding-adamw-through-proximal-methods-1","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","date":"2022-01-31","arxiv_id":"2202.00089","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/scrolls-standardized-comparison-over-long","slug":"scrolls-standardized-comparison-over-long","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","date":"2022-01-10","arxiv_id":"2201.03533","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":4,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tau-nlp/scrolls"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-convnet-for-the-2020s","slug":"a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","arxiv_id":"2201.03545","n_code_links":54,"syntology":{"ran":57,"of":80,"n_ran_checked":49,"n_instrument":8,"unverified":23,"pointer_only":12,"phrase":"57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 0 violated, 48 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified","official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/primer-pyramid-based-masked-sentence-pre","slug":"primer-pyramid-based-masked-sentence-pre","title":"PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization","date":"2021-10-16","arxiv_id":"2110.08499","n_code_links":3,"syntology":{"ran":7,"of":7,"n_ran_checked":4,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"7 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/primer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/2103-15358","slug":"2103-15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","date":"2021-03-29","arxiv_id":"2103.15358","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["microsoft/vision-longformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/swin-transformer-hierarchical-vision","slug":"swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","n_code_links":80,"syntology":{"ran":123,"of":207,"n_ran_checked":82,"n_instrument":41,"unverified":84,"pointer_only":45,"phrase":"123 ran (of which 45 constructed an object rather than computing a result; 82 with no instrument failure: 5 honoured, 2 violated, 75 with no contract checked; 41 where Syntology's instrument failed) · 84 unverified","official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"paper":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","n_code_links":40,"syntology":{"ran":12,"of":19,"n_ran_checked":9,"n_instrument":3,"unverified":7,"pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adahessian-an-adaptive-second-order-optimizer","slug":"adahessian-an-adaptive-second-order-optimizer","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","date":"2020-06-01","arxiv_id":"2006.00719","n_code_links":4,"syntology":{"ran":5,"of":11,"n_ran_checked":4,"n_instrument":1,"unverified":6,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["amirgholami/adahessian"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/longformer-the-long-document-transformer","slug":"longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","n_code_links":22,"syntology":{"ran":22,"of":35,"n_ran_checked":14,"n_instrument":8,"unverified":13,"pointer_only":5,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","official":{"repos":["allenai/longformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/stochastic-gradient-methods-with-layer-wise","slug":"stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","date":"2019-05-27","arxiv_id":"1905.11286","n_code_links":3,"syntology":{"ran":13,"of":16,"n_ran_checked":12,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/decoupled-weight-decay-regularization","slug":"decoupled-weight-decay-regularization","title":"Decoupled Weight Decay Regularization","date":"2017-11-14","arxiv_id":"1711.05101","n_code_links":23,"syntology":{"ran":18,"of":23,"n_ran_checked":18,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["GLambard/AdamW_Keras","Yagami123/Caffe-AdamW-AdamWR","loshchil/AdamW-and-SGDW"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"1742daa9b03edee1718d656db3959ecf1fc8322cd9ca946adb5e36f9be08ced3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}