{"task":"Visual Reasoning","dataset":"NLVR2 Dev","metric_names":["Accuracy"],"rows":[{"id":31683,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"BEiT-3","metrics":{"Accuracy":"91.51"},"paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","paper_date":"2022-08-22","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/beit"},{"title":"lyan62/data-curation","url":"https://github.com/lyan62/data-curation"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31684,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"X2-VLM (large)","metrics":{"Accuracy":"88.7"},"paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","paper_date":"2022-11-22","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"},{"title":"zengyan-97/x2-vlm","url":"https://github.com/zengyan-97/x2-vlm"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31685,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"XFM (base)","metrics":{"Accuracy":"87.6"},"paper_url":"https://arxiv.org/abs/2301.05065v2","paper_title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","paper_date":"2023-01-12","code_links":[{"title":"zhangxinsong-nlp/XFM","url":"https://github.com/zhangxinsong-nlp/XFM"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31686,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"X2-VLM (base)","metrics":{"Accuracy":"86.2"},"paper_url":"https://arxiv.org/abs/2211.12402v2","paper_title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","paper_date":"2022-11-22","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"},{"title":"zengyan-97/x2-vlm","url":"https://github.com/zengyan-97/x2-vlm"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31687,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"CoCa","metrics":{"Accuracy":"86.1"},"paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","paper_date":"2022-05-04","code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"amitakamath/whatsup_vlms","url":"https://github.com/amitakamath/whatsup_vlms"},{"title":"amitakamath/hard_positives","url":"https://github.com/amitakamath/hard_positives"},{"title":"Chaolei98/FreeZAD","url":"https://github.com/Chaolei98/FreeZAD"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31688,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"VLMo","metrics":{"Accuracy":"85.64"},"paper_url":"https://arxiv.org/abs/2111.02358v2","paper_title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","paper_date":"2021-11-03","code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/vlmo"},{"title":"ylsung/vl-merging","url":"https://github.com/ylsung/vl-merging"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31689,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"VK-OOD","metrics":{"Accuracy":"84.6"},"paper_url":"https://openreview.net/forum?id=jooPcatnVF","paper_title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","paper_date":"2023-09-21","code_links":[{"title":"ellenzhuwang/implicit_vkood","url":"https://github.com/ellenzhuwang/implicit_vkood"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31690,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"SimVLM","metrics":{"Accuracy":"84.53"},"paper_url":"https://arxiv.org/abs/2108.10904v3","paper_title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","paper_date":"2021-08-24","code_links":[{"title":"yulong-XJTU/SimVLM","url":"https://github.com/yulong-XJTU/SimVLM"},{"title":"FerryHuang/SimVLM","url":"https://github.com/FerryHuang/SimVLM"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31691,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"X-VLM (base)","metrics":{"Accuracy":"84.41"},"paper_url":"https://arxiv.org/abs/2111.08276v3","paper_title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","paper_date":"2021-11-16","code_links":[{"title":"zengyan-97/x-vlm","url":"https://github.com/zengyan-97/x-vlm"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31692,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"VK-OOD","metrics":{"Accuracy":"83.9"},"paper_url":"https://arxiv.org/abs/2302.05608v1","paper_title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","paper_date":"2023-02-11","code_links":[{"title":"ellenzhuwang/VK_OOD","url":"https://github.com/ellenzhuwang/VK_OOD"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31693,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"ALBEF (14M)","metrics":{"Accuracy":"83.14"},"paper_url":"https://arxiv.org/abs/2107.07651v2","paper_title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","paper_date":"2021-07-16","code_links":[{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"salesforce/ALBEF","url":"https://github.com/salesforce/ALBEF"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"amazon-research/mix-generation","url":"https://github.com/amazon-research/mix-generation"},{"title":"salesforce/pb-ovd","url":"https://github.com/salesforce/pb-ovd"},{"title":"yuliangcai2022/clumo","url":"https://github.com/yuliangcai2022/clumo"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31694,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"SOHO","metrics":{"Accuracy":"76.37"},"paper_url":"https://arxiv.org/abs/2104.03135v2","paper_title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","paper_date":"2021-04-07","code_links":[{"title":"researchmm/soho","url":"https://github.com/researchmm/soho"},{"title":"PasserBy4/mypretraining","url":"https://github.com/PasserBy4/mypretraining"},{"title":"PasserBy4/pretraining","url":"https://github.com/PasserBy4/pretraining"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31695,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"ViLT-B/32","metrics":{"Accuracy":"75.7"},"paper_url":"https://arxiv.org/abs/2102.03334v2","paper_title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","paper_date":"2021-02-05","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"dandelin/vilt","url":"https://github.com/dandelin/vilt"},{"title":"glamor-usc/climb","url":"https://github.com/glamor-usc/climb"},{"title":"guilk/vlc","url":"https://github.com/guilk/vlc"},{"title":"wglab/gestaltmml","url":"https://github.com/wglab/gestaltmml"},{"title":"wglab/gestaltmml-gestaltgpt","url":"https://github.com/wglab/gestaltmml-gestaltgpt"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31696,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"LXMERT (Pre-train + scratch)","metrics":{"Accuracy":"74.9"},"paper_url":"https://arxiv.org/abs/1908.07490v3","paper_title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","paper_date":"2019-08-20","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"airsplay/lxmert","url":"https://github.com/airsplay/lxmert"},{"title":"zhegan27/VILLA","url":"https://github.com/zhegan27/VILLA"},{"title":"zhegan27/LXMERT-AdvTrain","url":"https://github.com/zhegan27/LXMERT-AdvTrain"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"itsShnik/adaptively-finetuning-transformers","url":"https://github.com/itsShnik/adaptively-finetuning-transformers"},{"title":"ghazaleh-mahmoodi/lxmert_compression","url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression"},{"title":"chaitanyadwivedii/3D-Attention-is-All-You-Need","url":"https://github.com/chaitanyadwivedii/3D-Attention-is-All-You-Need"},{"title":"Mind23-2/MindCode-156","url":"https://github.com/Mind23-2/MindCode-156"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":31697,"task":"Visual Reasoning","parent_task":null,"dataset":"NLVR2 Dev","model_name":"VisualBERT","metrics":{"Accuracy":"66.7"},"paper_url":"https://arxiv.org/abs/1908.03557v1","paper_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","paper_date":"2019-08-09","code_links":[{"title":"uclanlp/visualbert","url":"https://github.com/uclanlp/visualbert"},{"title":"YIKUAN8/Transformers-VQA","url":"https://github.com/YIKUAN8/Transformers-VQA"},{"title":"lalithjets/surgical_vqa","url":"https://github.com/lalithjets/surgical_vqa"},{"title":"gchhablani/multilingual-vqa","url":"https://github.com/gchhablani/multilingual-vqa"},{"title":"longbai1006/surgical-vqla","url":"https://github.com/longbai1006/surgical-vqla"},{"title":"social-ai-studio/matk","url":"https://github.com/social-ai-studio/matk"},{"title":"chenkangyang/paddle_visual_bert","url":"https://github.com/chenkangyang/paddle_visual_bert"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/visual_bert"},{"title":"MindCode-4/code-1","url":"https://github.com/MindCode-4/code-1/tree/main/visual_bert"}],"metrics_order":"[\"Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}