{"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":"/dataset/imagenet-r","name":"ImageNet-R","full_name":"ImageNet-Rendition","description_markdown":"ImageNet-R(endition) contains art, cartoons, deviantart, graffiti, embroidery, graphics, origami, paintings, patterns, plastic objects, plush objects, sculptures, sketches, tattoos, toys, and video game renditions of ImageNet classes.\r\n\r\nImageNet-R has renditions of 200 ImageNet classes resulting in 30,000 images.\r\n\r\nSource: [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](/paper/the-many-faces-of-robustness-a-critical)","description_withheld":null,"homepage":"https://github.com/hendrycks/imagenet-r","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-many-faces-of-robustness-a-critical","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","first_author":"Dan Hendrycks","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Domain Generalization","url":"/task/domain-generalization","datasets_with_task":"/datasets/task/domain-generalization"},{"name":"Zero-Shot Transfer Image Classification","url":"/task/zero-shot-transfer-image-classification","datasets_with_task":"/datasets/task/zero-shot-transfer-image-classification"},{"name":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Zero-Shot Composed Image Retrieval (ZS-CIR)","url":"/task/zero-shot-composed-image-retrieval-zs-cir","datasets_with_task":"/datasets/task/zero-shot-composed-image-retrieval-zs-cir"},{"name":"Zero-shot Image Retrieval","url":"/task/zero-shot-image-retrieval","datasets_with_task":"/datasets/task/zero-shot-image-retrieval"}],"languages":[],"variants":["ImageNet-R"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/imagenet_r","frameworks":["tf","jax"]},{"repo":"https://github.com/ensta-u2is/torch-uncertainty","url":"https://torch-uncertainty.github.io/","frameworks":["pytorch"]},{"repo":"https://github.com/hendrycks/imagenet-r","url":"https://github.com/hendrycks/imagenet-r","frameworks":["pytorch"]}],"num_papers_in_archive":481,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset_variant":"ImageNet-R","rows":39,"metrics":["Top-1 Error Rate"],"first_row_in_archive_order":{"model":"Model soups (BASIC-L)","paper":"/paper/model-soups-averaging-weights-of-multiple","metrics":{"Top-1 Error Rate":"3.90"},"code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-composed-image-retrieval-zs-cir-on-6","task":"Zero-Shot Composed Image Retrieval (ZS-CIR)","dataset_variant":"ImageNet-R","rows":20,"metrics":["(Recall@10+Recall@50)/2","mAP"],"first_row_in_archive_order":{"model":"MagicLens (CoCa L)","paper":"/paper/magiclens-self-supervised-image-retrieval","metrics":{"(Recall@10+Recall@50)/2":"52.95"},"code_links":[{"title":"google-deepmind/magiclens","url":"https://github.com/google-deepmind/magiclens"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset_variant":"ImageNet-R","rows":12,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BASIC (Lion)","paper":null,"metrics":{"Accuracy":"96.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/prompt-engineering-on-imagenet-r","task":"Prompt Engineering","dataset_variant":"ImageNet-R","rows":9,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"POMP","paper":"/paper/prompt-pre-training-with-twenty-thousand-1","metrics":{"Top-1 accuracy %":"77.9"},"code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-imagenet-r","task":"Unsupervised Domain Adaptation","dataset_variant":"ImageNet-R","rows":8,"metrics":["Top 1 Error"],"first_row_in_archive_order":{"model":"Model soups (ViT-G/14)","paper":"/paper/model-soups-averaging-weights-of-multiple","metrics":{"Top 1 Error":"4.54"},"code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":50,"of":50,"counts":{"papers_with_a_benchmark_row":50,"with_a_code_link":48,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/mmrl-multi-modal-representation-learning-for","slug":"mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08497","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yunncheng/MMRL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmrl-multi-modal-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2503.08497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08497"}}}},{"paper":"/paper/composed-image-retrieval-for-training-free","slug":"composed-image-retrieval-for-training-free","title":"Composed Image Retrieval for Training-Free Domain Conversion","date":"2024-12-04","arxiv_id":"2412.03297","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","slug":"hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","arxiv_id":"2408.14812","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/isearle-improving-textual-inversion-for-zero","slug":"isearle-improving-textual-inversion-for-zero","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","date":"2024-05-05","arxiv_id":"2405.02951","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["miccunifi/circo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/isearle-improving-textual-inversion-for-zero#ran","syntology_url":"https://syntology.ai/paper/2405.02951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02951"}}}},{"paper":"/paper/magiclens-self-supervised-image-retrieval","slug":"magiclens-self-supervised-image-retrieval","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","date":"2024-03-28","arxiv_id":"2403.19651","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-deepmind/magiclens"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magiclens-self-supervised-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2403.19651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19651"}}}},{"paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","slug":"eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","arxiv_id":"2402.04252","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["baaivision/eva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-18b-scaling-clip-to-18-billion#ran","syntology_url":"https://syntology.ai/paper/2402.04252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04252"}}}},{"paper":"/paper/fully-attentional-networks-with-self-emerging-1","slug":"fully-attentional-networks-with-self-emerging-1","title":"Fully Attentional Networks with Self-emerging Token Labeling","date":"2024-01-08","arxiv_id":"2401.03844","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-hierarchical-prompt-with-structured","slug":"learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06323","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["vill-lab/2024-aaai-hpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-hierarchical-prompt-with-structured#ran","syntology_url":"https://syntology.ai/paper/2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}}}},{"paper":"/paper/language-only-efficient-training-of-zero-shot","slug":"language-only-efficient-training-of-zero-shot","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","date":"2023-12-04","arxiv_id":"2312.01998","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["navervision/lincir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-only-efficient-training-of-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2312.01998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01998"}}}},{"paper":"/paper/distilling-out-of-distribution-robustness-1","slug":"distilling-out-of-distribution-robustness-1","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","date":"2023-11-02","arxiv_id":"2311.01441","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["lapisrocks/DiscreteAdversarialDistillation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-out-of-distribution-robustness-1#ran","syntology_url":"https://syntology.ai/paper/2311.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01441"}}}},{"paper":"/paper/context-i2w-mapping-images-to-context","slug":"context-i2w-mapping-images-to-context","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","date":"2023-09-28","arxiv_id":"2309.16137","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["pter61/context-i2w"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/context-i2w-mapping-images-to-context#ran","syntology_url":"https://syntology.ai/paper/2309.16137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16137"}}}},{"paper":"/paper/self-regulating-prompts-foundational-model","slug":"self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","arxiv_id":"2307.06948","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["muzairkhattak/promptsrc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-regulating-prompts-foundational-model#ran","syntology_url":"https://syntology.ai/paper/2307.06948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06948"}}}},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","slug":"consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","arxiv_id":"2306.01195","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["shuvenduroy/coprompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/consistency-guided-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2306.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01195"}}}},{"paper":"/paper/prompt-pre-training-with-twenty-thousand-1","slug":"prompt-pre-training-with-twenty-thousand-1","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","date":"2023-04-10","arxiv_id":"2304.04704","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}}}},{"paper":"/paper/eva-clip-improved-training-techniques-for","slug":"eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","arxiv_id":"2303.15389","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}}}},{"paper":"/paper/zero-shot-composed-image-retrieval-with","slug":"zero-shot-composed-image-retrieval-with","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","date":"2023-03-27","arxiv_id":"2303.15247","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/scaling-vision-transformers-to-22-billion","slug":"scaling-vision-transformers-to-22-billion","title":"Scaling Vision Transformers to 22 Billion Parameters","date":"2023-02-10","arxiv_id":"2302.05442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pic2word-mapping-pictures-to-words-for-zero","slug":"pic2word-mapping-pictures-to-words-for-zero","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","date":"2023-02-06","arxiv_id":"2302.03084","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/composed_image_retrieval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pic2word-mapping-pictures-to-words-for-zero#ran","syntology_url":"https://syntology.ai/paper/2302.03084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03084"}}}},{"paper":"/paper/a-whac-a-mole-dilemma-shortcuts-come-in","slug":"a-whac-a-mole-dilemma-shortcuts-come-in","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","date":"2022-12-09","arxiv_id":"2212.04825","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-robust-fine-tuning","slug":"context-aware-robust-fine-tuning","title":"Context-Aware Robust Fine-Tuning","date":"2022-11-29","arxiv_id":"2211.16175","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/altclip-altering-the-language-encoder-in-clip#ran","syntology_url":"https://syntology.ai/paper/2211.06679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06679"}}}},{"paper":"/paper/metaformer-baselines-for-vision","slug":"metaformer-baselines-for-vision","title":"MetaFormer Baselines for Vision","date":"2022-10-24","arxiv_id":"2210.13452","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/metaformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metaformer-baselines-for-vision#ran","syntology_url":"https://syntology.ai/paper/2210.13452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13452"}}}},{"paper":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/maple-multi-modal-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2210.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03117"}}}},{"paper":"/paper/generalized-parametric-contrastive-learning","slug":"generalized-parametric-contrastive-learning","title":"Generalized Parametric Contrastive Learning","date":"2022-09-26","arxiv_id":"2209.12400","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/enhance-the-visual-representation-via","slug":"enhance-the-visual-representation-via","title":"Enhance the Visual Representation via Discrete Adversarial Training","date":"2022-09-16","arxiv_id":"2209.07735","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["alibaba/easyrobust"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/enhance-the-visual-representation-via#ran","syntology_url":"https://syntology.ai/paper/2209.07735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07735"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/sequencer-deep-lstm-for-image-classification","slug":"sequencer-deep-lstm-for-image-classification","title":"Sequencer: Deep LSTM for Image Classification","date":"2022-05-04","arxiv_id":"2205.01972","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["okojoalg/sequencer","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sequencer-deep-lstm-for-image-classification#ran","syntology_url":"https://syntology.ai/paper/2205.01972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01972"}}}},{"paper":"/paper/understanding-the-robustness-in-vision","slug":"understanding-the-robustness-in-vision","title":"Understanding The Robustness in Vision Transformers","date":"2022-04-26","arxiv_id":"2204.12451","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improving-vision-transformers-by-revisiting","slug":"improving-vision-transformers-by-revisiting","title":"Improving Vision Transformers by Revisiting High-frequency Components","date":"2022-04-03","arxiv_id":"2204.00993","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["jiawangbai/HAT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-vision-transformers-by-revisiting#ran","syntology_url":"https://syntology.ai/paper/2204.00993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00993"}}}},{"paper":"/paper/conditional-prompt-learning-for-vision","slug":"conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","arxiv_id":"2203.05557","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["kaiyangzhou/coop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/conditional-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2203.05557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05557"}}}},{"paper":"/paper/model-soups-averaging-weights-of-multiple","slug":"model-soups-averaging-weights-of-multiple","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","date":"2022-03-10","arxiv_id":"2203.05482","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["mlfoundations/model-soups"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/model-soups-averaging-weights-of-multiple#ran","syntology_url":"https://syntology.ai/paper/2203.05482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05482"}}}},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","slug":"vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","arxiv_id":"2202.08360","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-convnet-for-the-2020s","slug":"a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","arxiv_id":"2201.03545","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":80,"samples_ran":57,"samples_constructed":39,"samples_ran_checked":49,"samples_ran_instrument_failed":8,"samples_unverified":23,"pointer_only_for_licence":12,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"paper":"/paper/prime-a-few-primitives-can-boost-robustness","slug":"prime-a-few-primitives-can-boost-robustness","title":"PRIME: A few primitives can boost robustness to common corruptions","date":"2021-12-27","arxiv_id":"2112.13547","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["amodas/PRIME-augmentations"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prime-a-few-primitives-can-boost-robustness#ran","syntology_url":"https://syntology.ai/paper/2112.13547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13547"}}}},{"paper":"/paper/pyramid-adversarial-training-improves-vit","slug":"pyramid-adversarial-training-improves-vit","title":"Pyramid Adversarial Training Improves ViT Performance","date":"2021-11-30","arxiv_id":"2111.15121","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/discrete-representations-strengthen-vision-1","slug":"discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","date":"2021-11-20","arxiv_id":"2111.10493","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/combined-scaling-for-zero-shot-transfer","slug":"combined-scaling-for-zero-shot-transfer","title":"Combined Scaling for Zero-shot Transfer Learning","date":"2021-11-19","arxiv_id":"2111.10050","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lit-zero-shot-transfer-with-locked-image-text","slug":"lit-zero-shot-transfer-with-locked-image-text","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","date":"2021-11-15","arxiv_id":"2111.07991","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/masked-autoencoders-are-scalable-vision","slug":"masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","arxiv_id":"2111.06377","rows_on_this_dataset":1,"code_links":58,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":137,"samples_ran":86,"samples_constructed":40,"samples_ran_checked":68,"samples_ran_instrument_failed":18,"samples_unverified":51,"pointer_only_for_licence":78,"official":{"repos":["facebookresearch/mae"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"paper":"/paper/when-vision-transformers-outperform-resnets","slug":"when-vision-transformers-outperform-resnets","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","date":"2021-06-03","arxiv_id":"2106.01548","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/rethinking-the-design-principles-of-robust","slug":"rethinking-the-design-principles-of-robust","title":"Towards Robust Vision Transformer","date":"2021-05-17","arxiv_id":"2105.07926","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/adapting-imagenet-scale-models-to-complex","slug":"adapting-imagenet-scale-models-to-complex","title":"If your data distribution shifts, use self-learning","date":"2021-04-27","arxiv_id":"2104.12928","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/adapting-imagenet-scale-models-to-complex#ran","syntology_url":"https://syntology.ai/paper/2104.12928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12928"}}}},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":2,"code_links":82,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}}}},{"paper":"/paper/improving-robustness-against-common","slug":"improving-robustness-against-common","title":"Improving robustness against common corruptions by covariate shift adaptation","date":"2020-06-30","arxiv_id":"2006.16971","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-robustness-against-common#ran","syntology_url":"https://syntology.ai/paper/2006.16971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16971"}}}},{"paper":"/paper/the-many-faces-of-robustness-a-critical","slug":"the-many-faces-of-robustness-a-critical","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","date":"2020-06-29","arxiv_id":"2006.16241","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":14,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":12,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hendrycks/imagenet-r"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-many-faces-of-robustness-a-critical#ran","syntology_url":"https://syntology.ai/paper/2006.16241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16241"}}}},{"paper":"/paper/augmix-a-simple-data-processing-method-to","slug":"augmix-a-simple-data-processing-method-to","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","date":"2019-12-05","arxiv_id":"1912.02781","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":51,"samples_ran":46,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":37,"samples_unverified":5,"pointer_only_for_licence":25,"official":{"repos":["google-research/augmix"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/augmix-a-simple-data-processing-method-to#ran","syntology_url":"https://syntology.ai/paper/1912.02781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02781"}}}},{"paper":"/paper/imagenet-trained-cnns-are-biased-towards","slug":"imagenet-trained-cnns-are-biased-towards","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","date":"2018-11-29","arxiv_id":"1811.12231","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["rgeirhos/Stylized-ImageNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imagenet-trained-cnns-are-biased-towards#ran","syntology_url":"https://syntology.ai/paper/1811.12231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12231"}}}},{"paper":"/paper/deep-residual-learning-for-image-recognition","slug":"deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","rows_on_this_dataset":1,"code_links":484,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":377,"samples_ran":254,"samples_constructed":108,"samples_ran_checked":163,"samples_ran_instrument_failed":91,"samples_unverified":123,"pointer_only_for_licence":193,"official":{"repos":["KaimingHe/resnet-1k-layers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mmrl-multi-modal-representation-learning-for","slug":"mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08497","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["yunncheng/MMRL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmrl-multi-modal-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2503.08497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08497"}}}},{"paper":"/paper/composed-image-retrieval-for-training-free","slug":"composed-image-retrieval-for-training-free","title":"Composed Image Retrieval for Training-Free Domain Conversion","date":"2024-12-04","arxiv_id":"2412.03297","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","slug":"hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","arxiv_id":"2408.14812","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/isearle-improving-textual-inversion-for-zero","slug":"isearle-improving-textual-inversion-for-zero","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","date":"2024-05-05","arxiv_id":"2405.02951","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":4,"official":{"repos":["miccunifi/circo"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/isearle-improving-textual-inversion-for-zero#ran","syntology_url":"https://syntology.ai/paper/2405.02951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02951"}}}},{"paper":"/paper/magiclens-self-supervised-image-retrieval","slug":"magiclens-self-supervised-image-retrieval","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","date":"2024-03-28","arxiv_id":"2403.19651","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-deepmind/magiclens"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/magiclens-self-supervised-image-retrieval#ran","syntology_url":"https://syntology.ai/paper/2403.19651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19651"}}}},{"paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","slug":"eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","arxiv_id":"2402.04252","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":4,"official":{"repos":["baaivision/eva"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-18b-scaling-clip-to-18-billion#ran","syntology_url":"https://syntology.ai/paper/2402.04252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04252"}}}},{"paper":"/paper/fully-attentional-networks-with-self-emerging-1","slug":"fully-attentional-networks-with-self-emerging-1","title":"Fully Attentional Networks with Self-emerging Token Labeling","date":"2024-01-08","arxiv_id":"2401.03844","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-hierarchical-prompt-with-structured","slug":"learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","arxiv_id":"2312.06323","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["vill-lab/2024-aaai-hpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-hierarchical-prompt-with-structured#ran","syntology_url":"https://syntology.ai/paper/2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}}}},{"paper":"/paper/language-only-efficient-training-of-zero-shot","slug":"language-only-efficient-training-of-zero-shot","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","date":"2023-12-04","arxiv_id":"2312.01998","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["navervision/lincir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-only-efficient-training-of-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2312.01998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01998"}}}},{"paper":"/paper/distilling-out-of-distribution-robustness-1","slug":"distilling-out-of-distribution-robustness-1","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","date":"2023-11-02","arxiv_id":"2311.01441","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["lapisrocks/DiscreteAdversarialDistillation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-out-of-distribution-robustness-1#ran","syntology_url":"https://syntology.ai/paper/2311.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01441"}}}},{"paper":"/paper/context-i2w-mapping-images-to-context","slug":"context-i2w-mapping-images-to-context","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","date":"2023-09-28","arxiv_id":"2309.16137","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["pter61/context-i2w"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/context-i2w-mapping-images-to-context#ran","syntology_url":"https://syntology.ai/paper/2309.16137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16137"}}}},{"paper":"/paper/self-regulating-prompts-foundational-model","slug":"self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","arxiv_id":"2307.06948","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":5,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["muzairkhattak/promptsrc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-regulating-prompts-foundational-model#ran","syntology_url":"https://syntology.ai/paper/2307.06948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06948"}}}},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","slug":"consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","arxiv_id":"2306.01195","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["shuvenduroy/coprompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/consistency-guided-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2306.01195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01195"}}}},{"paper":"/paper/prompt-pre-training-with-twenty-thousand-1","slug":"prompt-pre-training-with-twenty-thousand-1","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","date":"2023-04-10","arxiv_id":"2304.04704","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["amazon-science/prompt-pretraining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-pre-training-with-twenty-thousand-1#ran","syntology_url":"https://syntology.ai/paper/2304.04704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04704"}}}},{"paper":"/paper/eva-clip-improved-training-techniques-for","slug":"eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","arxiv_id":"2303.15389","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baaivision/eva"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/eva-clip-improved-training-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"}}}},{"paper":"/paper/zero-shot-composed-image-retrieval-with","slug":"zero-shot-composed-image-retrieval-with","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","date":"2023-03-27","arxiv_id":"2303.15247","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/scaling-vision-transformers-to-22-billion","slug":"scaling-vision-transformers-to-22-billion","title":"Scaling Vision Transformers to 22 Billion Parameters","date":"2023-02-10","arxiv_id":"2302.05442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pic2word-mapping-pictures-to-words-for-zero","slug":"pic2word-mapping-pictures-to-words-for-zero","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","date":"2023-02-06","arxiv_id":"2302.03084","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["google-research/composed_image_retrieval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pic2word-mapping-pictures-to-words-for-zero#ran","syntology_url":"https://syntology.ai/paper/2302.03084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03084"}}}},{"paper":"/paper/a-whac-a-mole-dilemma-shortcuts-come-in","slug":"a-whac-a-mole-dilemma-shortcuts-come-in","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","date":"2022-12-09","arxiv_id":"2212.04825","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-robust-fine-tuning","slug":"context-aware-robust-fine-tuning","title":"Context-Aware Robust Fine-Tuning","date":"2022-11-29","arxiv_id":"2211.16175","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/altclip-altering-the-language-encoder-in-clip","slug":"altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","arxiv_id":"2211.06679","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["flagai-open/flagai"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/altclip-altering-the-language-encoder-in-clip#ran","syntology_url":"https://syntology.ai/paper/2211.06679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.06679"}}}},{"paper":"/paper/metaformer-baselines-for-vision","slug":"metaformer-baselines-for-vision","title":"MetaFormer Baselines for Vision","date":"2022-10-24","arxiv_id":"2210.13452","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/metaformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/metaformer-baselines-for-vision#ran","syntology_url":"https://syntology.ai/paper/2210.13452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13452"}}}},{"paper":"/paper/maple-multi-modal-prompt-learning","slug":"maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","arxiv_id":"2210.03117","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["muzairkhattak/multimodal-prompt-learning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/maple-multi-modal-prompt-learning#ran","syntology_url":"https://syntology.ai/paper/2210.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03117"}}}},{"paper":"/paper/generalized-parametric-contrastive-learning","slug":"generalized-parametric-contrastive-learning","title":"Generalized Parametric Contrastive Learning","date":"2022-09-26","arxiv_id":"2209.12400","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/enhance-the-visual-representation-via","slug":"enhance-the-visual-representation-via","title":"Enhance the Visual Representation via Discrete Adversarial Training","date":"2022-09-16","arxiv_id":"2209.07735","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["alibaba/easyrobust"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/enhance-the-visual-representation-via#ran","syntology_url":"https://syntology.ai/paper/2209.07735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07735"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/sequencer-deep-lstm-for-image-classification","slug":"sequencer-deep-lstm-for-image-classification","title":"Sequencer: Deep LSTM for Image Classification","date":"2022-05-04","arxiv_id":"2205.01972","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["okojoalg/sequencer","rwightman/pytorch-image-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sequencer-deep-lstm-for-image-classification#ran","syntology_url":"https://syntology.ai/paper/2205.01972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01972"}}}},{"paper":"/paper/understanding-the-robustness-in-vision","slug":"understanding-the-robustness-in-vision","title":"Understanding The Robustness in Vision Transformers","date":"2022-04-26","arxiv_id":"2204.12451","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improving-vision-transformers-by-revisiting","slug":"improving-vision-transformers-by-revisiting","title":"Improving Vision Transformers by Revisiting High-frequency Components","date":"2022-04-03","arxiv_id":"2204.00993","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["jiawangbai/HAT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-vision-transformers-by-revisiting#ran","syntology_url":"https://syntology.ai/paper/2204.00993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.00993"}}}},{"paper":"/paper/conditional-prompt-learning-for-vision","slug":"conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","arxiv_id":"2203.05557","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["kaiyangzhou/coop"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/conditional-prompt-learning-for-vision#ran","syntology_url":"https://syntology.ai/paper/2203.05557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05557"}}}},{"paper":"/paper/model-soups-averaging-weights-of-multiple","slug":"model-soups-averaging-weights-of-multiple","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","date":"2022-03-10","arxiv_id":"2203.05482","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["mlfoundations/model-soups"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/model-soups-averaging-weights-of-multiple#ran","syntology_url":"https://syntology.ai/paper/2203.05482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05482"}}}},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","slug":"vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","arxiv_id":"2202.08360","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-convnet-for-the-2020s","slug":"a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","arxiv_id":"2201.03545","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":80,"samples_ran":57,"samples_constructed":39,"samples_ran_checked":49,"samples_ran_instrument_failed":8,"samples_unverified":23,"pointer_only_for_licence":12,"official":{"repos":["facebookresearch/ConvNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-convnet-for-the-2020s#ran","syntology_url":"https://syntology.ai/paper/2201.03545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03545"}}}},{"paper":"/paper/prime-a-few-primitives-can-boost-robustness","slug":"prime-a-few-primitives-can-boost-robustness","title":"PRIME: A few primitives can boost robustness to common corruptions","date":"2021-12-27","arxiv_id":"2112.13547","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["amodas/PRIME-augmentations"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prime-a-few-primitives-can-boost-robustness#ran","syntology_url":"https://syntology.ai/paper/2112.13547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13547"}}}},{"paper":"/paper/pyramid-adversarial-training-improves-vit","slug":"pyramid-adversarial-training-improves-vit","title":"Pyramid Adversarial Training Improves ViT Performance","date":"2021-11-30","arxiv_id":"2111.15121","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/discrete-representations-strengthen-vision-1","slug":"discrete-representations-strengthen-vision-1","title":"Discrete Representations Strengthen Vision Transformer Robustness","date":"2021-11-20","arxiv_id":"2111.10493","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/combined-scaling-for-zero-shot-transfer","slug":"combined-scaling-for-zero-shot-transfer","title":"Combined Scaling for Zero-shot Transfer Learning","date":"2021-11-19","arxiv_id":"2111.10050","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lit-zero-shot-transfer-with-locked-image-text","slug":"lit-zero-shot-transfer-with-locked-image-text","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","date":"2021-11-15","arxiv_id":"2111.07991","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/masked-autoencoders-are-scalable-vision","slug":"masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","arxiv_id":"2111.06377","rows_on_this_dataset":1,"code_links":58,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":137,"samples_ran":86,"samples_constructed":40,"samples_ran_checked":68,"samples_ran_instrument_failed":18,"samples_unverified":51,"pointer_only_for_licence":78,"official":{"repos":["facebookresearch/mae"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"paper":"/paper/when-vision-transformers-outperform-resnets","slug":"when-vision-transformers-outperform-resnets","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","date":"2021-06-03","arxiv_id":"2106.01548","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/rethinking-the-design-principles-of-robust","slug":"rethinking-the-design-principles-of-robust","title":"Towards Robust Vision Transformer","date":"2021-05-17","arxiv_id":"2105.07926","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/adapting-imagenet-scale-models-to-complex","slug":"adapting-imagenet-scale-models-to-complex","title":"If your data distribution shifts, use self-learning","date":"2021-04-27","arxiv_id":"2104.12928","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/adapting-imagenet-scale-models-to-complex#ran","syntology_url":"https://syntology.ai/paper/2104.12928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12928"}}}},{"paper":"/paper/learning-transferable-visual-models-from","slug":"learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","rows_on_this_dataset":2,"code_links":82,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":20,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":14,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["openai/CLIP"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-transferable-visual-models-from#ran","syntology_url":"https://syntology.ai/paper/2103.00020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00020"}}}},{"paper":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":6,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}}}},{"paper":"/paper/improving-robustness-against-common","slug":"improving-robustness-against-common","title":"Improving robustness against common corruptions by covariate shift adaptation","date":"2020-06-30","arxiv_id":"2006.16971","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bethgelab/robustness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/improving-robustness-against-common#ran","syntology_url":"https://syntology.ai/paper/2006.16971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16971"}}}},{"paper":"/paper/the-many-faces-of-robustness-a-critical","slug":"the-many-faces-of-robustness-a-critical","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","date":"2020-06-29","arxiv_id":"2006.16241","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":14,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":12,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["hendrycks/imagenet-r"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-many-faces-of-robustness-a-critical#ran","syntology_url":"https://syntology.ai/paper/2006.16241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.16241"}}}},{"paper":"/paper/augmix-a-simple-data-processing-method-to","slug":"augmix-a-simple-data-processing-method-to","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","date":"2019-12-05","arxiv_id":"1912.02781","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":51,"samples_ran":46,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":37,"samples_unverified":5,"pointer_only_for_licence":25,"official":{"repos":["google-research/augmix"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/augmix-a-simple-data-processing-method-to#ran","syntology_url":"https://syntology.ai/paper/1912.02781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02781"}}}},{"paper":"/paper/imagenet-trained-cnns-are-biased-towards","slug":"imagenet-trained-cnns-are-biased-towards","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","date":"2018-11-29","arxiv_id":"1811.12231","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["rgeirhos/Stylized-ImageNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/imagenet-trained-cnns-are-biased-towards#ran","syntology_url":"https://syntology.ai/paper/1811.12231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12231"}}}},{"paper":"/paper/deep-residual-learning-for-image-recognition","slug":"deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","rows_on_this_dataset":1,"code_links":484,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":377,"samples_ran":254,"samples_constructed":108,"samples_ran_checked":163,"samples_ran_instrument_failed":91,"samples_unverified":123,"pointer_only_for_licence":193,"official":{"repos":["KaimingHe/resnet-1k-layers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}}],"papers_where_code_ran":33,"papers_where_code_ran_first_page":"/dataset/imagenet-r/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/imagenet-r/papers/ran/1","json":"/dataset/imagenet-r/papers/ran/1.json","rows":33}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":34,"samples_harvested":876,"samples_ran":605,"samples_constructed":206,"samples_ran_checked":383,"samples_ran_instrument_failed":222,"samples_unverified":271,"pointer_only_for_licence":374,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":33,"papers_with_a_run_with_no_instrument_failure":30,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","since_archive":"/sota/zero-shot-transfer-image-classification-on-4#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"55622bc4cfc84b58542b0ac21927f555a82be65313d365051362fc397d11b472","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}