{"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/loft-low-rank-adaptation-that-behaves-like","title":"LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning","arxiv_id":"2505.21289","date":"2025-05-27","proceeding":null,"authors":["Nurbek Tastan","Stefanos Laskaridis","Martin Takac","Karthik Nandakumar","Samuel Horvath"],"abstract":"Large pre-trained models are commonly adapted to downstream tasks using parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA), which injects small trainable low-rank matrices instead of updating all weights. While LoRA dramatically reduces trainable parameters with little overhead, it can still underperform full fine-tuning in accuracy and often converges more slowly. We introduce LoFT, a novel low-rank adaptation method that behaves like full fine-tuning by aligning the optimizer's internal dynamics with those of updating all model weights. LoFT not only learns weight updates in a low-rank subspace (like LoRA) but also properly projects the optimizer's first and second moments (Adam's momentum and variance) into the same subspace, mirroring full-model updates. By aligning the low-rank update itself with the full update, LoFT eliminates the need for tuning extra hyperparameters, e.g., LoRA scaling factor $\\alpha$. Empirically, this approach substantially narrows the performance gap between adapter-based tuning and full fine-tuning and consistently outperforms standard LoRA-style methods, all without increasing inference cost.","url_abs":"https://arxiv.org/abs/2505.21289v1","url_pdf":"https://arxiv.org/pdf/2505.21289v1.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":[],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.21289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21289"}},"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":"deterministic:regex_extraction","url":"https://github.com/tnurbek/loft","reach":null}],"summary":{"ran":1,"ran_fixture":4,"ran_draft_wrong":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":9,"ran":7,"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":"c6158005ab8589b5","entry":"LoFTAdamW","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6158005ab8589b5"}},{"code_sha256_prefix":"9a2ec6a670678efb","entry":"compute_full_grad_from_proj","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a2ec6a670678efb"}},{"code_sha256_prefix":"3eb4c0c3fbdc880d","entry":"compute_mom_sq_from_row_prod_and_transformation","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb4c0c3fbdc880d"}},{"code_sha256_prefix":"8a7a0a901ee57322","entry":"do_update_","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a7a0a901ee57322"}},{"code_sha256_prefix":"a5311761d3c05643","entry":"get_reprojected_momentum","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5311761d3c05643"}},{"code_sha256_prefix":"26e5fc043cc0c851","entry":"get_reprojected_second_moment","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26e5fc043cc0c851"}},{"code_sha256_prefix":"5193d9d48000c46b","entry":"rescale_gradients","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5193d9d48000c46b"}},{"code_sha256_prefix":"4c04bcf45359e67c","entry":"compute_proj_update","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","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":"4c04bcf45359e67c"}},{"code_sha256_prefix":"9a8d4f5881387ef2","entry":"get_mom_reprojection","repo":"tnurbek/loft","repo_kind":"found_in_text","path":"loft_optim/optimizer.py","file_url":"https://github.com/tnurbek/loft/blob/HEAD/loft_optim/optimizer.py","link_basis":"first_harvest_node","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":"9a8d4f5881387ef2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}