{"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":"/paper/model-merging-with-svd-to-tie-the-knots","title":"Model merging with SVD to tie the Knots","arxiv_id":"2410.19735","date":"2024-10-25","proceeding":null,"authors":["George Stoica","Pratik Ramesh","Boglarka Ecsedi","Leshem Choshen","Judy Hoffman"],"abstract":"Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does not transfer well when merging LoRA finetuned models. We study this phenomenon and observe that the weights of LoRA finetuned models showcase a lower degree of alignment compared to their fully-finetuned counterparts. We hypothesize that improving this alignment is key to obtaining better LoRA model merges, and propose KnOTS to address this problem. KnOTS uses the SVD to jointly transform the weights of different LoRA models into an aligned space, where existing merging methods can be applied. In addition, we introduce a new benchmark that explicitly evaluates whether merged models are general models. Notably, KnOTS consistently improves LoRA merging by up to 4.3% across several vision and language benchmarks, including our new setting. We release our code at: https://github.com/gstoica27/KnOTS.","url_abs":"https://arxiv.org/abs/2410.19735v1","url_pdf":"https://arxiv.org/pdf/2410.19735v1.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":"model-merging-with-svd-to-tie-the-knots","repo_url":"https://github.com/gstoica27/knots","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.19735","atlas_url":"https://app.syntology.ai/?focus=2410.19735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19735"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.19735"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.19735"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.19735\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.19735"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.19735\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.19735"},"call":"get_concepts_for_paper(arxiv_id=\"2410.19735\")"}],"by_repo":[{"repo":"gstoica27/knots","kind":"official","samples":6,"ran":5,"instrument":4,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.19735.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.19735.svg"},"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/gstoica27/knots","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":4,"ran":1,"unverified":1},"n_samples":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"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)"},"by_repo_kind":{"official":{"samples":6,"ran":5,"n_ran_checked":1,"n_instrument":4,"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":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":3,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"70e49dc222d0391a","code_sha256_prefix":"70e49dc222d0391a","entry":"resolve_sign","repo":"gstoica27/knots","repo_kind":"official","path":"masking_ops.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/masking_ops.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"Tensor:Tensor/2/float, mode:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from CaoAnda/ENMP-LoRAMerging, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"70e49dc222d0391a"}},{"code_sha256":"860408c2bd01950e","code_sha256_prefix":"860408c2bd01950e","entry":"resolve_zero_signs","repo":"gstoica27/knots","repo_kind":"official","path":"masking_ops.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/masking_ops.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"sign_to_mult:Tensor/1/float, method:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"860408c2bd01950e"},"code_page":null,"census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from thunlp-mt/adamms, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"860408c2bd01950e"}},{"code_sha256":"f6ead996d6b1adba","code_sha256_prefix":"f6ead996d6b1adba","entry":"topk_values_mask","repo":"gstoica27/knots","repo_kind":"official","path":"merging_functions.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/merging_functions.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"M:Tensor/2/float, K:float/0/float, return_mask:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/topk-values-mask","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f6ead996d6b1adba"}},{"code_sha256":"cc25fa48e243d80b","code_sha256_prefix":"cc25fa48e243d80b","entry":"topk_values_mask","repo":"gstoica27/knots","repo_kind":"official","path":"masking_ops.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/masking_ops.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"M:Tensor/2/float, K:float/0/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cc25fa48e243d80b"},"code_page":"/code/topk-values-mask","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from CaoAnda/ENMP-LoRAMerging, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"cc25fa48e243d80b"}},{"code_sha256":"3521eec6c7977199","code_sha256_prefix":"3521eec6c7977199","entry":"tv_merging","repo":"gstoica27/knots","repo_kind":"official","path":"merging_functions.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/merging_functions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"vectors:list/1/Tensor, weights:list/1/float, merging_type:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3521eec6c7977199"}},{"code_sha256":"1937c8308a2b4783","code_sha256_prefix":"1937c8308a2b4783","entry":"get_model_from_config","repo":"gstoica27/knots","repo_kind":"official","path":"models/huggingface_clip.py","file_url":"https://github.com/gstoica27/knots/blob/HEAD/models/huggingface_clip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1937c8308a2b4783"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4fde911ce6f496f15f9ad07ba97eb4d28ec218c3743afc4d8dc63200767b7b9a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}