{"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/cpt-colorful-prompt-tuning-for-pre-trained","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","arxiv_id":"2109.11797","date":"2021-09-24","proceeding":null,"authors":["Yuan YAO","Ao Zhang","Zhengyan Zhang","Zhiyuan Liu","Tat-Seng Chua","Maosong Sun"],"abstract":"Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks. However, we note that there exists a significant gap between the objective forms of model pre-training and fine-tuning, resulting in a need for large amounts of labeled data to stimulate the visual grounding capability of VL-PTMs for downstream tasks. To address the challenge, we present Cross-modal Prompt Tuning (CPT, alternatively, Colorful Prompt Tuning), a novel paradigm for tuning VL-PTMs, which reformulates visual grounding into a fill-in-the-blank problem with color-based co-referential markers in image and text, maximally mitigating the gap. In this way, CPT enables strong few-shot and even zero-shot visual grounding capabilities of VL-PTMs. Comprehensive experimental results show that the prompt-tuned VL-PTMs outperform their fine-tuned counterparts by a large margin (e.g., 17.3% absolute accuracy improvement, and 73.8% relative standard deviation reduction on average with one shot in RefCOCO evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/CPT.","url_abs":"https://arxiv.org/abs/2109.11797v3","url_pdf":"https://arxiv.org/pdf/2109.11797v3.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":"cpt-colorful-prompt-tuning-for-pre-trained","repo_url":"https://github.com/thunlp/cpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cpt-colorful-prompt-tuning-for-pre-trained","repo_url":"https://github.com/lunaproject22/rpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.11797","atlas_url":"https://app.syntology.ai/?focus=2109.11797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11797"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.11797"},"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":"2109.11797"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.11797\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2109.11797"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.11797\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.11797"},"call":"get_concepts_for_paper(arxiv_id=\"2109.11797\")"}],"by_repo":[{"repo":"thunlp/cpt","kind":"official","samples":13,"ran":12,"instrument":2,"unverified":1},{"repo":"lunaproject22/rpa","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2202.04800"],"harvested_for_calls":[{"arxiv_id":"2202.04800","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.04800"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.04800\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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/2109.11797.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/2109.11797.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/thunlp/cpt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lunaproject22/rpa","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"ran_draft_wrong":2,"unverified":1},"n_samples":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"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":13,"ran":12,"n_ran_checked":10,"n_instrument":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":2,"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":2,"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":10,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","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":"89bdd6decba2b415","code_sha256_prefix":"89bdd6decba2b415","entry":"compute_score_with_logits","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/gqa_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/gqa_cpt.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"logits:Tensor/2/float, labels:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"89bdd6decba2b415"},"code_page":"/code/compute-score-with-logits","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"89bdd6decba2b415"}},{"code_sha256":"01da88ba6172509e","code_sha256_prefix":"01da88ba6172509e","entry":"get_evaluate_file","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/refcoco_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/refcoco_cpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"predict_file:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"01da88ba6172509e"}},{"code_sha256":"e040a3d039f5af10","code_sha256_prefix":"e040a3d039f5af10","entry":"get_evaluate_method","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/refcoco_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/refcoco_cpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"predict_file:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","retrieve_with":{"tool":"get_code","code_sha256":"e040a3d039f5af10"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e040a3d039f5af10"}},{"code_sha256":"e36ec4e0a52c6a4b","code_sha256_prefix":"e36ec4e0a52c6a4b","entry":"instance_bce_with_logits","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/gqa_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/gqa_cpt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"logits:Tensor/2/float, labels:Tensor/2/float, reduction:str/0/str","fixture_out_type":"Tensor","code_page":"/code/instance-bce-with-logits","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 linweizhedragon/retrieval-augmented-visual-question-answering, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"e36ec4e0a52c6a4b"}},{"code_sha256":"d48bb07bc01dfdb7","code_sha256_prefix":"d48bb07bc01dfdb7","entry":"template1","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"caption:str/0/str, posi_tokens:Tensor/1/int","fixture_out_type":"str","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d48bb07bc01dfdb7"}},{"code_sha256":"c0fd672552e0160f","code_sha256_prefix":"c0fd672552e0160f","entry":"template2","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"caption:str/0/str, posi_tokens:Tensor/2/float","fixture_out_type":"str","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c0fd672552e0160f"}},{"code_sha256":"39e9626ebfd96e62","code_sha256_prefix":"39e9626ebfd96e62","entry":"template3","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/refcoco_zsl_cpt_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"caption:str/0/str, posi_tokens:Tensor/2/int","fixture_out_type":"str","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":"39e9626ebfd96e62"}},{"code_sha256":"7ab756d02fb91e21","code_sha256_prefix":"7ab756d02fb91e21","entry":"tokenize","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/datasets/refcoco_fsl_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/refcoco_fsl_cpt_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:MinimalTokenizer/0/?, text_a:str/0/str, text_b:str/0/str, img_feat:Tensor/2/float, max_img_seq_len:int/0/int, max_seq_a_len:int/0/int, max_seq_len:int/0/int, cls_token_segment_id:int/0/int, pad_token_segment_id:int/0/int, sequence_a_segment_id:int/0/int, sequence_b_segment_id:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":"/code/tokenize","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7ab756d02fb91e21"}},{"code_sha256":"0a1867725d8d31b1","code_sha256_prefix":"0a1867725d8d31b1","entry":"tokenize","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/datasets/vg_cpt_dataset.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/datasets/vg_cpt_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:MockTokenizer/0/?, text_a:str/0/str, text_b:str/0/str, img_feat:Tensor/2/float, max_img_seq_len:int/0/int, max_seq_a_len:int/0/int, max_seq_len:int/0/int, cls_token_segment_id:int/0/int, pad_token_segment_id:int/0/int, sequence_a_segment_id:int/0/int, sequence_b_segment_id:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":"/code/tokenize","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0a1867725d8d31b1"}},{"code_sha256":"12516cd21b436092","code_sha256_prefix":"12516cd21b436092","entry":"trim_batch","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/gqa_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/gqa_cpt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"batch:list/1/list","fixture_out_type":"list","code_page":"/code/trim-batch","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 linweizhedragon/retrieval-augmented-visual-question-answering, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline","mcp_get_code":{"code_sha256":"12516cd21b436092"}},{"code_sha256":"2e1b1ca48e16a324","code_sha256_prefix":"2e1b1ca48e16a324","entry":"vcr_collate_fn","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/vcr_nsp_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/vcr_nsp_cpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"batch:list/1/tuple","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2e1b1ca48e16a324"}},{"code_sha256":"ffe4043326409d20","code_sha256_prefix":"ffe4043326409d20","entry":"vcr_collate_fn","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/vcr_qar_nsp_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/vcr_qar_nsp_cpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"raw_batch:list/1/tuple","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T23:53:12.863503+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ffe4043326409d20"}},{"code_sha256":"5ddea353591c2338","code_sha256_prefix":"5ddea353591c2338","entry":"restore_training_settings","repo":"thunlp/cpt","repo_kind":"official","path":"Oscar/oscar/fewshot/refcoco_cpt.py","file_url":"https://github.com/thunlp/cpt/blob/HEAD/Oscar/oscar/fewshot/refcoco_cpt.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":"5ddea353591c2338"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dd7dc3386bfabcd7061362cfe680821ddc73eb5eb77c18d12905479f423cfae3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}