{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","arxiv_id":"2301.12597","date":"2023-01-30","proceeding":"Conference 2023 2","authors":["Junnan Li","Dongxu Li","Silvio Savarese","Steven Hoi"],"abstract":"The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large language models. BLIP-2 bridges the modality gap with a lightweight Querying Transformer, which is pre-trained in two stages. The first stage bootstraps vision-language representation learning from a frozen image encoder. The second stage bootstraps vision-to-language generative learning from a frozen language model. BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods. For example, our model outperforms Flamingo80B by 8.7% on zero-shot VQAv2 with 54x fewer trainable parameters. We also demonstrate the model's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.","url_abs":"https://arxiv.org/abs/2301.12597v3","url_pdf":"https://arxiv.org/pdf/2301.12597v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/salesforce/lavis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/albertotestoni/ndq_visual_objects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/alibaba/graphtranslator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/baaivision/eva","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/facebookresearch/multimodal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/gregor-ge/mblip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/jiwanchung/vlis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/junshutang/Make-It-3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/kdr/videorag-mrr2024","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/linzhiqiu/clip-flant5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/rabiulcste/vqazero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/thudm/visualglm-6b","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/yukw777/videoblip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"generative-visual-question-answering","task_name":"Generative Visual Question Answering"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"medical-visual-question-answering","task_name":"Medical Visual Question Answering"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"open-vocabulary-attribute-detection","task_name":"Open Vocabulary Attribute Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-text-to-image-retrieval","task_name":"Zero-shot Text-to-Image Retrieval"},{"task_slug":"visual-instruction-following","task_name":"visual instruction following"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generative-visual-question-answering-on-pmc","task":"Generative Visual Question Answering","dataset":"PMC-VQA","model":"BLIP-2","rank_in_archive_order":2,"of":3,"metrics":{"BLEU-1":"7.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":4,"of":41,"metrics":{"BLEU-4":"43.7","CIDER":"145.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":5,"of":41,"metrics":{"BLEU-4":"43.5","CIDER":"145.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":8,"of":41,"metrics":{"BLEU-4":"42.4","CIDER":"144.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"CIDEr":"123.7","Pre-train (#images)":"1.1B","SPICE":"16.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":11,"metrics":{"CIDEr":"123.7","Pre-train (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"CIDEr":"123","Pre-train (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":10,"metrics":{"CIDEr":"120.2","Pre-train (#images)":"1.1B","SPICE":"15.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":10,"metrics":{"CIDEr":"119.2","Pre-train (#images)":"1.1B","SPICE":"15.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":10,"metrics":{"CIDEr":"117.8","Pre-train (#images)":"1.1B","SPICE":"15.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":10,"metrics":{"CIDEr":"124.8","Pretrain (#images)":"1.1B","SPICE":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":10,"metrics":{"CIDEr":"124.4","Pretrain (#images)":"1.1B","SPICE":"14.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":10,"metrics":{"CIDEr":"123.4","Pretrain (#images)":"1.1B","SPICE":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"CIDEr":"121.6","Pretrain (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":11,"metrics":{"CIDEr":"121.0","Pretrain (#images)":"1.1B","SPICE":"15.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"CIDEr":"119.7","Pretrain (#images)":"1.1B","SPICE":"15.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-coco","task":"Image Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 ViT-G (fine-tuned)","rank_in_archive_order":1,"of":6,"metrics":{"Recall@10":"92.6","recall@1":"68.3","recall@5":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-coco","task":"Image Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 ViT-L (fine-tuned)","rank_in_archive_order":3,"of":6,"metrics":{"Recall@10":"91.8","recall@1":"66.3","recall@5":"86.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-G (zero-shot, 1K test set)","rank_in_archive_order":1,"of":9,"metrics":{"Recall@1":"89.7","Recall@10":"98.9","Recall@5":"98.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-L (zero-shot, 1K test set)","rank_in_archive_order":2,"of":9,"metrics":{"Recall@1":"88.6","Recall@10":"98.9","Recall@5":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 (ViT-G, fine-tuned)","rank_in_archive_order":1,"of":9,"metrics":{"Recall@1":"85.4","Recall@10":"98.5","Recall@5":"97.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 (ViT-L, fine-tuned)","rank_in_archive_order":3,"of":9,"metrics":{"Recall@1":"83.5","Recall@10":"98.0","Recall@5":"96.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-G (zero-shot, 1K test set)","rank_in_archive_order":2,"of":11,"metrics":{"Recall@1":"97.6","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-L (zero-shot, 1K test set)","rank_in_archive_order":5,"of":11,"metrics":{"Recall@1":"96.9","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-attribute-detection-on-ovad-1","task":"Open Vocabulary Attribute Detection","dataset":"OVAD-Box benchmark","model":"BLIP 2 (pretrained)","rank_in_archive_order":2,"of":7,"metrics":{"mean average precision":"25.5"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"BLIP-2-12B","rank_in_archive_order":226,"of":231,"metrics":{"GPT-4 score":"22.4±0.2","Params":"12B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","rank_in_archive_order":1,"of":11,"metrics":{"Accuracy":"82.30"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 2.7B (fine-tuned)","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy":"81.74"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XL (fine-tuned)","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"81.66"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"82.19"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 2.7B (fine-tuned)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"81.59"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XL (fine-tuned)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"81.55"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":10,"of":17,"metrics":{"Accuracy":"44.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":11,"of":17,"metrics":{"Accuracy":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":12,"of":17,"metrics":{"Accuracy":"44.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":14,"of":17,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":15,"of":17,"metrics":{"Accuracy":"34.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":16,"of":17,"metrics":{"Accuracy":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-core-mm","task":"Visual Question Answering (VQA)","dataset":"InfiMM-Eval","model":"BLIP-2-OPT2.7B","rank_in_archive_order":12,"of":14,"metrics":{"Abductive":"18.96","Analogical":"7.5","Deductive":"2.76","Overall score":"19.31","Params":"3B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-infoseek","task":"Visual Question Answering (VQA)","dataset":"InfoSeek","model":"BLIP2","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"14.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":23,"of":37,"metrics":{"Accuracy":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":28,"of":37,"metrics":{"Accuracy":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":29,"of":37,"metrics":{"Accuracy":"39.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":30,"of":37,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":32,"of":37,"metrics":{"Accuracy":"31.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":33,"of":37,"metrics":{"Accuracy":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-pmc-vqa","task":"Visual Question Answering (VQA)","dataset":"PMC-VQA","model":"BLIP-2","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"24.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":42,"of":56,"metrics":{"Accuracy":"65"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":47,"of":56,"metrics":{"Accuracy":"63"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":48,"of":56,"metrics":{"Accuracy":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":50,"of":56,"metrics":{"Accuracy":"52.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":51,"of":56,"metrics":{"Accuracy":"52.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":54,"of":56,"metrics":{"Accuracy":"49.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"Accuracy":"65.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"Accuracy":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy":"62.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":6,"of":11,"metrics":{"Accuracy":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":7,"of":11,"metrics":{"Accuracy":"50.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-instruction-following-on-llava-bench","task":"visual instruction following","dataset":"LLaVA-Bench","model":"BLIP-2","rank_in_archive_order":8,"of":8,"metrics":{"avg score":"38.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/lavis","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yukw777/videoblip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rabiulcste/vqazero","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/albertotestoni/ndq_visual_objects","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiwanchung/vlis","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gregor-ge/mblip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baaivision/eva","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/visualglm-6b","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linzhiqiu/clip-flant5","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junshutang/Make-It-3D","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kdr/videorag-mrr2024","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/graphtranslator","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/multimodal","reach":null}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"listed":{"samples":8,"ran":4,"repositories":4}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"dbb9b4ef6b0f95dd","entry":"BLIP2","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dbb9b4ef6b0f95dd"}},{"code_sha256_prefix":"b939479f3d2573b8","entry":"Blip2Output","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b939479f3d2573b8"}},{"code_sha256_prefix":"196ad3b77304e23c","entry":"CLIPT5Config","repo":"linzhiqiu/clip-flant5","repo_kind":"listed","path":"llava/model/language_model/clip_t5.py","file_url":"https://github.com/linzhiqiu/clip-flant5/blob/HEAD/llava/model/language_model/clip_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"196ad3b77304e23c"}},{"code_sha256_prefix":"e62bffe433f61ff1","entry":"TransformerOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e62bffe433f61ff1"}},{"code_sha256_prefix":"11e6ad12cf0667b0","entry":"CLIPT5ForConditionalGeneration","repo":"linzhiqiu/clip-flant5","repo_kind":"listed","path":"llava/model/language_model/clip_t5.py","file_url":"https://github.com/linzhiqiu/clip-flant5/blob/HEAD/llava/model/language_model/clip_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"11e6ad12cf0667b0"}},{"code_sha256_prefix":"6e342d36cf541d23","entry":"LynxBase","repo":"jiwanchung/vlis","repo_kind":"listed","path":"code/lynx/lynx_llm/models/lynx.py","file_url":"https://github.com/jiwanchung/vlis/blob/HEAD/code/lynx/lynx_llm/models/lynx.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e342d36cf541d23"}},{"code_sha256_prefix":"b67db6a1705fb783","entry":"VideoBlipForConditionalGeneration","repo":"yukw777/videoblip","repo_kind":"listed","path":"video_blip/model.py","file_url":"https://github.com/yukw777/videoblip/blob/HEAD/video_blip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b67db6a1705fb783"}},{"code_sha256_prefix":"c4125cdecc4964aa","entry":"VideoBlipVisionModel","repo":"yukw777/videoblip","repo_kind":"listed","path":"video_blip/model.py","file_url":"https://github.com/yukw777/videoblip/blob/HEAD/video_blip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4125cdecc4964aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}