{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/merge-3-efficient-evolutionary-merging-on","title":"MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs","arxiv_id":"2502.10436","date":"2025-02-09","proceeding":null,"authors":["Tommaso Mencattini","Adrian Robert Minut","Donato Crisostomi","Andrea Santilli","Emanuele Rodolà"],"abstract":"Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for consumer hardware. We introduce MERGE$^3$, an efficient framework that makes evolutionary merging feasible on a single GPU by reducing fitness computation costs 50$\\times$ while preserving performance. MERGE$^3$ achieves this by Extracting a reduced dataset for evaluation, Estimating model abilities using Item Response Theory (IRT), and Evolving optimal merges via IRT-based performance estimators. Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead. We provide theoretical guarantees and an open-source library, democratizing high-quality model merging.","url_abs":"https://arxiv.org/abs/2502.10436v4","url_pdf":"https://arxiv.org/pdf/2502.10436v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"merge-3-efficient-evolutionary-merging-on","repo_url":"https://github.com/tommasomncttn/merge3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.10436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10436"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tommasomncttn/merge3","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_violates":1,"unverified":12},"by_repo_kind":{"official":{"samples":14,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"921caf5fc3c2b540","entry":"item_curve","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/evaluation/perf_estimation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/evaluation/perf_estimation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"921caf5fc3c2b540"}},{"code_sha256_prefix":"a911f9cacbc9faf4","entry":"sigmoid","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/evaluation/perf_estimation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/evaluation/perf_estimation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a911f9cacbc9faf4"}},{"code_sha256_prefix":"aecf0f6af92bdbea","entry":"check_file_exists","repo":"tommasomncttn/merge3","repo_kind":"official","path":"experiments/end2end_utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/experiments/end2end_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aecf0f6af92bdbea"}},{"code_sha256_prefix":"ad669d6920f1ab84","entry":"control_if_basin_empty","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad669d6920f1ab84"}},{"code_sha256_prefix":"e4bfa2dbc5c77b3f","entry":"cosine_metric","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/analysis/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4bfa2dbc5c77b3f"}},{"code_sha256_prefix":"322193f8e999747b","entry":"euclidean_distance","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/analysis/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"322193f8e999747b"}},{"code_sha256_prefix":"990fcd8a91251235","entry":"evaluate","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/evaluation/perf_estimation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/evaluation/perf_estimation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"990fcd8a91251235"}},{"code_sha256_prefix":"dc5e6f0b0d3e0338","entry":"get_batched_model_predictions","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc5e6f0b0d3e0338"}},{"code_sha256_prefix":"ae535f3632a7a319","entry":"get_closest_embeddings_indices","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/extraction/extract.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/extraction/extract.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae535f3632a7a319"}},{"code_sha256_prefix":"98becc383cf5defb","entry":"get_clusters","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/extraction/extract.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/extraction/extract.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98becc383cf5defb"}},{"code_sha256_prefix":"1286c013573044fc","entry":"get_embeddings","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/analysis/representation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/representation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1286c013573044fc"}},{"code_sha256_prefix":"5c61d04821edf18d","entry":"get_representations","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/analysis/representation.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/representation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c61d04821edf18d"}},{"code_sha256_prefix":"7f86d24773127cc9","entry":"locate_base_folder","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f86d24773127cc9"}},{"code_sha256_prefix":"254de3d2da6d51ac","entry":"mean_aggregation","repo":"tommasomncttn/merge3","repo_kind":"official","path":"src/mergenetic/analysis/utils.py","file_url":"https://github.com/tommasomncttn/merge3/blob/HEAD/src/mergenetic/analysis/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"254de3d2da6d51ac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}