{"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/soups","slug":"soups","name":"Soups","full_name":"Model Soups","full_name_withheld":false,"description_markdown":"Compress an ensemble of models into a single one by averaging their weights (under certain pre-conditions).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","paper":"/paper/model-soups-averaging-weights-of-multiple","first_author":"Mitchell Wortsman","n_authors":11,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/model-soups-averaging-weights-of-multiple"},"source":{"url":"https://arxiv.org/abs/2203.05482v3","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Model Compression","url":"/methods/category/model-compression","pwc_aliases":[]}],"n_papers_tagged":19,"archive_num_papers":19,"papers_newest_first":[{"paper":null,"slug":"uc-moa-utility-conditioned-multi-objective","title":"UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality","date":"2025-03-10","arxiv_id":"2503.10669","n_code_links":0,"syntology":null},{"paper":"/paper/local-superior-soups-a-catalyst-for-model","slug":"local-superior-soups-a-catalyst-for-model","title":"Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning","date":"2024-10-31","arxiv_id":"2410.23660","n_code_links":1,"syntology":{"ran":4,"of":12,"n_ran_checked":2,"n_instrument":2,"unverified":8,"pointer_only":12,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["ubc-tea/local-superior-soups"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/merging-in-a-bottle-differentiable-adaptive","slug":"merging-in-a-bottle-differentiable-adaptive","title":"Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation","date":"2024-10-10","arxiv_id":"2410.08371","n_code_links":1,"syntology":null},{"paper":null,"slug":"robust-biharmonic-skinning-using-geometric","title":"Robust Biharmonic Skinning Using Geometric Fields","date":"2024-06-01","arxiv_id":"2406.00238","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-dataset-generalization-for-retinal","title":"Cross-Dataset Generalization For Retinal Lesions Segmentation","date":"2024-05-14","arxiv_id":"2405.08329","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-much-you-ate-food-portion-estimation-on","title":"How Much You Ate? Food Portion Estimation on Spoons","date":"2024-05-12","arxiv_id":"2405.08717","n_code_links":0,"syntology":null},{"paper":"/paper/fissionfusion-fast-geometric-generation-and","slug":"fissionfusion-fast-geometric-generation-and","title":"FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis","date":"2024-03-20","arxiv_id":"2403.13341","n_code_links":1,"syntology":null},{"paper":null,"slug":"radin-souping-on-a-budget","title":"RADIN: Souping on a Budget","date":"2024-01-31","arxiv_id":"2401.17790","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-fine-tuning-a-successor-to-full-fine","title":"Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers","date":"2023-12-25","arxiv_id":"2312.15681","n_code_links":0,"syntology":null},{"paper":"/paper/descriptor-and-word-soups-overcoming-the","slug":"descriptor-and-word-soups-overcoming-the","title":"Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning","date":"2023-11-21","arxiv_id":"2311.13612","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-model-soups-a-recipe-for-improved","slug":"sparse-model-soups-a-recipe-for-improved","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","date":"2023-06-29","arxiv_id":"2306.16788","n_code_links":1,"syntology":null},{"paper":"/paper/graph-ladling-shockingly-simple-parallel-gnn","slug":"graph-ladling-shockingly-simple-parallel-gnn","title":"Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication","date":"2023-06-18","arxiv_id":"2306.10466","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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vita-group/graph_ladling"],"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":null,"slug":"pre-training-language-model-as-a-multi","title":"Pre-training Language Model as a Multi-perspective Course Learner","date":"2023-05-06","arxiv_id":"2305.03981","n_code_links":0,"syntology":null},{"paper":null,"slug":"seasoning-model-soups-for-robustness-to","title":"Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts","date":"2023-02-20","arxiv_id":"2302.10164","n_code_links":0,"syntology":null},{"paper":"/paper/candidate-soups-fusing-candidate-results","slug":"candidate-soups-fusing-candidate-results","title":"Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation","date":"2023-01-27","arxiv_id":"2301.11503","n_code_links":1,"syntology":null},{"paper":"/paper/model-soups-to-increase-inference-without","slug":"model-soups-to-increase-inference-without","title":"Model soups to increase inference without increasing compute time","date":"2023-01-24","arxiv_id":"2301.10092","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-adapters-with-adversarial-training","title":"Revisiting adapters with adversarial training","date":"2022-10-10","arxiv_id":"2210.04886","n_code_links":0,"syntology":null},{"paper":"/paper/bag-of-tricks-for-domain-adaptive-multi","slug":"bag-of-tricks-for-domain-adaptive-multi","title":"Bag of Tricks for Domain Adaptive Multi-Object Tracking","date":"2022-05-31","arxiv_id":"2205.15609","n_code_links":1,"syntology":null},{"paper":"/paper/model-soups-averaging-weights-of-multiple","slug":"model-soups-averaging-weights-of-multiple","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","date":"2022-03-10","arxiv_id":"2203.05482","n_code_links":6,"syntology":{"ran":10,"of":17,"n_ran_checked":5,"n_instrument":5,"unverified":7,"pointer_only":0,"phrase":"10 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; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["mlfoundations/model-soups"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":19,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":19,"with_a_code_link":10,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":19,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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":3,"papers_where_code_ran_first_page":"/method/soups/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/soups/papers/ran/1","json":"/method/soups/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/domain-generalization","name":"Domain Generalization","papers":2},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":1},{"task":"/task/federated-learning","name":"Federated Learning","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/graph-sampling","name":"Graph Sampling","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":1},{"task":"/task/medical-image-analysis","name":"Medical Image Analysis","papers":1},{"task":"/task/model-compression","name":"Model Compression","papers":1},{"task":"/task/multi-object-tracking","name":"Multi-Object Tracking","papers":1},{"task":"/task/object-tracking","name":"Object Tracking","papers":1},{"task":"/task/out-of-distribution-generalization","name":"Out-of-Distribution Generalization","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/translation","name":"Translation","papers":1},{"task":"/task/unsupervised-domain-adaptation","name":"Unsupervised Domain Adaptation","papers":1},{"task":"/task/graph-partitioning","name":"graph partitioning","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1}],"tasks_shown":20,"n_tasks":22,"usage_by_year":[{"year":"2022","papers":3},{"year":"2023","papers":8},{"year":"2024","papers":7},{"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/soups"},"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=Soups","read_at":"2026-10-05T01:02:16+00:00","query":"Soups","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":"2203.05482","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 'Soups' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["LT-Soups","Local Superior Soups"],"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":"98c05fcc2ae0ce30ded755a04f24249eafba60488a075dc479afaeb9d9d03b77","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}