{"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/coco-captions","name":"COCO Captions","full_name":null,"description_markdown":"COCO Captions contains over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions are be provided for each image.\r\n\r\nSource: [Microsoft COCO Captions: Data Collection and Evaluation Server](https://arxiv.org/abs/1504.00325)","description_withheld":null,"homepage":"https://github.com/tylin/coco-caption","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/microsoft-coco-captions-data-collection-and","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","first_author":"Xinlei Chen","url":null},"license":{"name":"CC BY","url":"https://cocodataset.org/#termsofuse"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Concept-To-Text Generation","url":"/task/concept-to-text-generation","datasets_with_task":"/datasets/task/concept-to-text-generation"}],"languages":[],"variants":["COCO Captions","COCO Captions test","Image Captioning on COCO Captions","COCO Captions Karpathy Test"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.CocoCaptions.html","frameworks":["pytorch"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#coco_captions","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/coco_captions","frameworks":["tf","jax"]},{"repo":"https://github.com/tylin/coco-caption","url":"https://github.com/tylin/coco-caption","frameworks":[]}],"num_papers_in_archive":203,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset_variant":"COCO Captions","rows":41,"metrics":["BLEU-4","CIDER","METEOR","SPICE","ROUGE-L","BLEU-1","BLEU-2","BLEU-3","CLIPScore"],"first_row_in_archive_order":{"model":"mPLUG","paper":"/paper/mplug-effective-and-efficient-vision-language","metrics":{"BLEU-4":"46.5","CIDER":"155.1","METEOR":"32.0","SPICE":"26.0"},"code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind/tree/main/mPLUG"},{"title":"x-plug/mplug","url":"https://github.com/x-plug/mplug"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-coco-captions","task":"Text Generation","dataset_variant":"COCO Captions","rows":5,"metrics":["BLEU-2","BLEU-3","BLEU-4","BLEU-5"],"first_row_in_archive_order":{"model":"LeakGAN","paper":"/paper/long-text-generation-via-adversarial-training","metrics":{"BLEU-2":"0.950","BLEU-3":"0.880","BLEU-4":"0.778","BLEU-5":"0.686"},"code_links":[{"title":"CR-Gjx/LeakGAN","url":"https://github.com/CR-Gjx/LeakGAN"},{"title":"nurpeiis/LeakGAN-PyTorch","url":"https://github.com/nurpeiis/LeakGAN-PyTorch"},{"title":"valko073/LyricsGANs","url":"https://github.com/valko073/LyricsGANs"},{"title":"rupes438/CodeGen","url":"https://github.com/rupes438/CodeGen"},{"title":"liyzcj/leakgan-py3","url":"https://github.com/liyzcj/leakgan-py3"},{"title":"universebh/text_generation_fsa_gan","url":"https://github.com/universebh/text_generation_fsa_gan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-captioning-on-coco-captions-test","task":"Image Captioning","dataset_variant":"COCO Captions test","rows":2,"metrics":["BLEU-4","CIDEr","METEOR","SPICE"],"first_row_in_archive_order":{"model":"From Captions to Visual Concepts and Back","paper":"/paper/from-captions-to-visual-concepts-and-back","metrics":{"BLEU-4":"56.7","CIDEr":"92.5","METEOR":"33.1"},"code_links":[{"title":"s-gupta/visual-concepts","url":"https://github.com/s-gupta/visual-concepts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/concept-to-text-generation-on-coco-captions","task":"Concept-To-Text Generation","dataset_variant":"COCO Captions","rows":1,"metrics":["BLEU-2"],"first_row_in_archive_order":{"model":"tecpic","paper":"/paper/fake-news-detection-as-natural-language","metrics":{"BLEU-2":"2"},"code_links":[{"title":"zake7749/WSDM-Cup-2019","url":"https://github.com/zake7749/WSDM-Cup-2019"}]},"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":40,"of":40,"counts":{"papers_with_a_benchmark_row":40,"with_a_code_link":36,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/ladic-are-diffusion-models-really-inferior-to","slug":"ladic-are-diffusion-models-really-inferior-to","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","date":"2024-04-16","arxiv_id":"2404.10763","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/fusecap-leveraging-large-language-models-to","slug":"fusecap-leveraging-large-language-models-to","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","date":"2023-05-28","arxiv_id":"2305.17718","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/prismer-a-vision-language-model-with-an","slug":"prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","arxiv_id":"2303.02506","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","rows_on_this_dataset":3,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["salesforce/lavis"],"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/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}}}},{"paper":"/paper/position-guided-text-prompt-for-vision","slug":"position-guided-text-prompt-for-vision","title":"Position-guided Text Prompt for Vision-Language Pre-training","date":"2022-12-19","arxiv_id":"2212.09737","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sail-sg/ptp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/position-guided-text-prompt-for-vision#ran","syntology_url":"https://syntology.ai/paper/2212.09737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09737"}}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["davidhuji/capdec"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-only-training-for-image-captioning-using#ran","syntology_url":"https://syntology.ai/paper/2211.00575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00575"}}}},{"paper":"/paper/smallcap-lightweight-image-captioning","slug":"smallcap-lightweight-image-captioning","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","date":"2022-09-30","arxiv_id":"2209.15323","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/expansionnet-v2-block-static-expansion-in","slug":"expansionnet-v2-block-static-expansion-in","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","date":"2022-08-13","arxiv_id":"2208.06551","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/prompt-tuning-for-generative-multimodal","slug":"prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","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":1,"official":{"repos":["ofa-sys/ofa"],"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/prompt-tuning-for-generative-multimodal#ran","syntology_url":"https://syntology.ai/paper/2208.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02532"}}}},{"paper":"/paper/grit-faster-and-better-image-captioning","slug":"grit-faster-and-better-image-captioning","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","date":"2022-07-20","arxiv_id":"2207.09666","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}}}},{"paper":"/paper/fine-grained-image-captioning-with-clip","slug":"fine-grained-image-captioning-with-clip","title":"Fine-grained Image Captioning with CLIP Reward","date":"2022-05-26","arxiv_id":"2205.13115","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/beyond-a-pre-trained-object-detector-cross","slug":"beyond-a-pre-trained-object-detector-cross","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","date":"2022-05-09","arxiv_id":"2205.04363","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"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/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","rows_on_this_dataset":1,"code_links":4,"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":["ofa-sys/ofa"],"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}}}},{"paper":"/paper/scaling-up-vision-language-pre-training-for","slug":"scaling-up-vision-language-pre-training-for","title":"Scaling Up Vision-Language Pre-training for Image Captioning","date":"2021-11-24","arxiv_id":"2111.12233","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/l-verse-bidirectional-generation-between","slug":"l-verse-bidirectional-generation-between","title":"L-Verse: Bidirectional Generation Between Image and Text","date":"2021-11-22","arxiv_id":"2111.11133","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clipcap-clip-prefix-for-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2111.09734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09734"}}}},{"paper":"/paper/enabling-multimodal-generation-on-clip-via","slug":"enabling-multimodal-generation-on-clip-via","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","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":["zengyan-97/x-vlm"],"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/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}}}},{"paper":"/paper/refinecap-concept-aware-refinement-for-image","slug":"refinecap-concept-aware-refinement-for-image","title":"RefineCap: Concept-Aware Refinement for Image Captioning","date":"2021-09-08","arxiv_id":"2109.03529","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":22,"samples_constructed":8,"samples_ran_checked":16,"samples_ran_instrument_failed":6,"samples_unverified":15,"pointer_only_for_licence":32,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}}}},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":1,"code_links":7,"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":1,"official":{"repos":["pzzhang/VinVL"],"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/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/virtex-learning-visual-representations-from","slug":"virtex-learning-visual-representations-from","title":"VirTex: Learning Visual Representations from Textual Annotations","date":"2020-06-11","arxiv_id":"2006.06666","rows_on_this_dataset":1,"code_links":3,"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":["kdexd/virtex"],"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/virtex-learning-visual-representations-from#ran","syntology_url":"https://syntology.ai/paper/2006.06666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06666"}}}},{"paper":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":13,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":1,"official":{"repos":["microsoft/Oscar"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}}}},{"paper":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-better-variant-of-self-critical-sequence","slug":"a-better-variant-of-self-critical-sequence","title":"A Better Variant of Self-Critical Sequence Training","date":"2020-03-22","arxiv_id":"2003.09971","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-commonsense-r-cnn","slug":"visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","date":"2020-02-27","arxiv_id":"2002.12204","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Wangt-CN/VC-R-CNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-commonsense-r-cnn#ran","syntology_url":"https://syntology.ai/paper/2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}}}},{"paper":"/paper/m2-meshed-memory-transformer-for-image","slug":"m2-meshed-memory-transformer-for-image","title":"Meshed-Memory Transformer for Image Captioning","date":"2019-12-17","arxiv_id":"1912.08226","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["aimagelab/meshed-memory-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/m2-meshed-memory-transformer-for-image#ran","syntology_url":"https://syntology.ai/paper/1912.08226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08226"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/reflective-decoding-network-for-image","slug":"reflective-decoding-network-for-image","title":"Reflective Decoding Network for Image Captioning","date":"2019-08-30","arxiv_id":"1908.11824","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-as-natural-language","slug":"fake-news-detection-as-natural-language","title":"Fake News Detection as Natural Language Inference","date":"2019-07-17","arxiv_id":"1907.07347","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/relgan-relational-generative-adversarial","slug":"relgan-relational-generative-adversarial","title":"RelGAN: Relational Generative Adversarial Networks for Text Generation","date":"2019-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/long-text-generation-via-adversarial-training","slug":"long-text-generation-via-adversarial-training","title":"Long Text Generation via Adversarial Training with Leaked Information","date":"2017-09-24","arxiv_id":"1709.08624","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["CR-Gjx/LeakGAN"],"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/long-text-generation-via-adversarial-training#ran","syntology_url":"https://syntology.ai/paper/1709.08624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.08624"}}}},{"paper":"/paper/adversarial-ranking-for-language-generation","slug":"adversarial-ranking-for-language-generation","title":"Adversarial Ranking for Language Generation","date":"2017-05-31","arxiv_id":"1705.11001","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/seqgan-sequence-generative-adversarial-nets","slug":"seqgan-sequence-generative-adversarial-nets","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","date":"2016-09-18","arxiv_id":"1609.05473","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":13,"official":{"repos":["LantaoYu/SeqGAN"],"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/seqgan-sequence-generative-adversarial-nets#ran","syntology_url":"https://syntology.ai/paper/1609.05473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.05473"}}}},{"paper":"/paper/from-captions-to-visual-concepts-and-back","slug":"from-captions-to-visual-concepts-and-back","title":"From Captions to Visual Concepts and Back","date":"2014-11-18","arxiv_id":"1411.4952","rows_on_this_dataset":2,"code_links":1,"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":0,"official":{"repos":["s-gupta/visual-concepts"],"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/from-captions-to-visual-concepts-and-back#ran","syntology_url":"https://syntology.ai/paper/1411.4952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1411.4952"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/ladic-are-diffusion-models-really-inferior-to","slug":"ladic-are-diffusion-models-really-inferior-to","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","date":"2024-04-16","arxiv_id":"2404.10763","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":42,"samples_ran":35,"samples_constructed":4,"samples_ran_checked":25,"samples_ran_instrument_failed":10,"samples_unverified":7,"pointer_only_for_licence":8,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"paper":"/paper/fusecap-leveraging-large-language-models-to","slug":"fusecap-leveraging-large-language-models-to","title":"FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions","date":"2023-05-28","arxiv_id":"2305.17718","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/prismer-a-vision-language-model-with-an","slug":"prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","arxiv_id":"2303.02506","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","rows_on_this_dataset":3,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["salesforce/lavis"],"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/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}}}},{"paper":"/paper/position-guided-text-prompt-for-vision","slug":"position-guided-text-prompt-for-vision","title":"Position-guided Text Prompt for Vision-Language Pre-training","date":"2022-12-19","arxiv_id":"2212.09737","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["sail-sg/ptp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/position-guided-text-prompt-for-vision#ran","syntology_url":"https://syntology.ai/paper/2212.09737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09737"}}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["davidhuji/capdec"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/text-only-training-for-image-captioning-using#ran","syntology_url":"https://syntology.ai/paper/2211.00575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00575"}}}},{"paper":"/paper/smallcap-lightweight-image-captioning","slug":"smallcap-lightweight-image-captioning","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","date":"2022-09-30","arxiv_id":"2209.15323","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/expansionnet-v2-block-static-expansion-in","slug":"expansionnet-v2-block-static-expansion-in","title":"Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning","date":"2022-08-13","arxiv_id":"2208.06551","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/prompt-tuning-for-generative-multimodal","slug":"prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","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":1,"official":{"repos":["ofa-sys/ofa"],"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/prompt-tuning-for-generative-multimodal#ran","syntology_url":"https://syntology.ai/paper/2208.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02532"}}}},{"paper":"/paper/grit-faster-and-better-image-captioning","slug":"grit-faster-and-better-image-captioning","title":"GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features","date":"2022-07-20","arxiv_id":"2207.09666","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}}}},{"paper":"/paper/fine-grained-image-captioning-with-clip","slug":"fine-grained-image-captioning-with-clip","title":"Fine-grained Image Captioning with CLIP Reward","date":"2022-05-26","arxiv_id":"2205.13115","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/beyond-a-pre-trained-object-detector-cross","slug":"beyond-a-pre-trained-object-detector-cross","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","date":"2022-05-09","arxiv_id":"2205.04363","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"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/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","rows_on_this_dataset":1,"code_links":4,"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":["ofa-sys/ofa"],"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/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}}}},{"paper":"/paper/scaling-up-vision-language-pre-training-for","slug":"scaling-up-vision-language-pre-training-for","title":"Scaling Up Vision-Language Pre-training for Image Captioning","date":"2021-11-24","arxiv_id":"2111.12233","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/l-verse-bidirectional-generation-between","slug":"l-verse-bidirectional-generation-between","title":"L-Verse: Bidirectional Generation Between Image and Text","date":"2021-11-22","arxiv_id":"2111.11133","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clipcap-clip-prefix-for-image-captioning","slug":"clipcap-clip-prefix-for-image-captioning","title":"ClipCap: CLIP Prefix for Image Captioning","date":"2021-11-18","arxiv_id":"2111.09734","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["rmokady/clip_prefix_caption"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clipcap-clip-prefix-for-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2111.09734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09734"}}}},{"paper":"/paper/enabling-multimodal-generation-on-clip-via","slug":"enabling-multimodal-generation-on-clip-via","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","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":["zengyan-97/x-vlm"],"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/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}}}},{"paper":"/paper/refinecap-concept-aware-refinement-for-image","slug":"refinecap-concept-aware-refinement-for-image","title":"RefineCap: Concept-Aware Refinement for Image Captioning","date":"2021-09-08","arxiv_id":"2109.03529","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":22,"samples_constructed":8,"samples_ran_checked":16,"samples_ran_instrument_failed":6,"samples_unverified":15,"pointer_only_for_licence":32,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}}}},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":1,"code_links":7,"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":1,"official":{"repos":["pzzhang/VinVL"],"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/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/virtex-learning-visual-representations-from","slug":"virtex-learning-visual-representations-from","title":"VirTex: Learning Visual Representations from Textual Annotations","date":"2020-06-11","arxiv_id":"2006.06666","rows_on_this_dataset":1,"code_links":3,"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":["kdexd/virtex"],"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/virtex-learning-visual-representations-from#ran","syntology_url":"https://syntology.ai/paper/2006.06666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06666"}}}},{"paper":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":13,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":1,"official":{"repos":["microsoft/Oscar"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}}}},{"paper":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/a-better-variant-of-self-critical-sequence","slug":"a-better-variant-of-self-critical-sequence","title":"A Better Variant of Self-Critical Sequence Training","date":"2020-03-22","arxiv_id":"2003.09971","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-commonsense-r-cnn","slug":"visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","date":"2020-02-27","arxiv_id":"2002.12204","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Wangt-CN/VC-R-CNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-commonsense-r-cnn#ran","syntology_url":"https://syntology.ai/paper/2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}}}},{"paper":"/paper/m2-meshed-memory-transformer-for-image","slug":"m2-meshed-memory-transformer-for-image","title":"Meshed-Memory Transformer for Image Captioning","date":"2019-12-17","arxiv_id":"1912.08226","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["aimagelab/meshed-memory-transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/m2-meshed-memory-transformer-for-image#ran","syntology_url":"https://syntology.ai/paper/1912.08226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08226"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/reflective-decoding-network-for-image","slug":"reflective-decoding-network-for-image","title":"Reflective Decoding Network for Image Captioning","date":"2019-08-30","arxiv_id":"1908.11824","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-as-natural-language","slug":"fake-news-detection-as-natural-language","title":"Fake News Detection as Natural Language Inference","date":"2019-07-17","arxiv_id":"1907.07347","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/relgan-relational-generative-adversarial","slug":"relgan-relational-generative-adversarial","title":"RelGAN: Relational Generative Adversarial Networks for Text Generation","date":"2019-05-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/long-text-generation-via-adversarial-training","slug":"long-text-generation-via-adversarial-training","title":"Long Text Generation via Adversarial Training with Leaked Information","date":"2017-09-24","arxiv_id":"1709.08624","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["CR-Gjx/LeakGAN"],"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/long-text-generation-via-adversarial-training#ran","syntology_url":"https://syntology.ai/paper/1709.08624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.08624"}}}},{"paper":"/paper/adversarial-ranking-for-language-generation","slug":"adversarial-ranking-for-language-generation","title":"Adversarial Ranking for Language Generation","date":"2017-05-31","arxiv_id":"1705.11001","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/seqgan-sequence-generative-adversarial-nets","slug":"seqgan-sequence-generative-adversarial-nets","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","date":"2016-09-18","arxiv_id":"1609.05473","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":7,"pointer_only_for_licence":13,"official":{"repos":["LantaoYu/SeqGAN"],"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/seqgan-sequence-generative-adversarial-nets#ran","syntology_url":"https://syntology.ai/paper/1609.05473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.05473"}}}},{"paper":"/paper/from-captions-to-visual-concepts-and-back","slug":"from-captions-to-visual-concepts-and-back","title":"From Captions to Visual Concepts and Back","date":"2014-11-18","arxiv_id":"1411.4952","rows_on_this_dataset":2,"code_links":1,"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":0,"official":{"repos":["s-gupta/visual-concepts"],"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/from-captions-to-visual-concepts-and-back#ran","syntology_url":"https://syntology.ai/paper/1411.4952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1411.4952"}}}}],"papers_where_code_ran":20,"papers_where_code_ran_first_page":"/dataset/coco-captions/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/coco-captions/papers/ran/1","json":"/dataset/coco-captions/papers/ran/1.json","rows":20}],"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":20,"samples_harvested":225,"samples_ran":158,"samples_constructed":27,"samples_ran_checked":119,"samples_ran_instrument_failed":39,"samples_unverified":67,"pointer_only_for_licence":82,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":20,"papers_with_a_run_with_no_instrument_failure":19,"papers_where_every_run_was_an_instrument_failure":1,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"37907c19cddf438bb7e080761f212e172bd8108c3ff49e657eae8e0404bc2663","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}