{"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/cross-modal-fine-tuning-align-then-refine","title":"Cross-Modal Fine-Tuning: Align then Refine","arxiv_id":"2302.05738","date":"2023-02-11","proceeding":null,"authors":["Junhong Shen","Liam Li","Lucio M. Dery","Corey Staten","Mikhail Khodak","Graham Neubig","Ameet Talwalkar"],"abstract":"Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models. In this work, we propose ORCA, a general cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities. ORCA adapts to a target task via an align-then-refine workflow: given the target input, ORCA first learns an embedding network that aligns the embedded feature distribution with the pretraining modality. The pretrained model is then fine-tuned on the embedded data to exploit the knowledge shared across modalities. Through extensive experiments, we show that ORCA obtains state-of-the-art results on 3 benchmarks containing over 60 datasets from 12 modalities, outperforming a wide range of hand-designed, AutoML, general-purpose, and task-specific methods. We highlight the importance of data alignment via a series of ablation studies and demonstrate ORCA's utility in data-limited regimes.","url_abs":"https://arxiv.org/abs/2302.05738v2","url_pdf":"https://arxiv.org/pdf/2302.05738v2.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":"cross-modal-fine-tuning-align-then-refine","repo_url":"https://github.com/sjunhongshen/orca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"automl","task_name":"AutoML"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.05738","atlas_url":"https://app.syntology.ai/?focus=2302.05738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05738"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/sjunhongshen/orca","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"823d6b42f7a9daeb","entry":"infer_labels","repo":"sjunhongshen/orca","repo_kind":"official","path":"src/embedder.py","file_url":"https://github.com/sjunhongshen/orca/blob/HEAD/src/embedder.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":"823d6b42f7a9daeb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}