{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"mlc-imp","owner":"MILVLG","isFork":true,"description":"Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":1397,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-29T13:31:34.183Z"}},{"type":"Public","name":"imp","owner":"MILVLG","isFork":false,"description":"a family of highly capabale yet efficient large multimodal models","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":144,"forksCount":14,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-26T07:49:40.246Z"}},{"type":"Public template","name":"anetqa","owner":"MILVLG","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"HTML","color":"#e34c26"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-15T23:56:51.171Z"}},{"type":"Public","name":"anetqa-code","owner":"MILVLG","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":9,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-07T08:00:06.563Z"}},{"type":"Public","name":"rosita","owner":"MILVLG","isFork":false,"description":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","allTopics":["vqa","vision-and-language","pre-training","referring-expression-comprehension","image-text-retrieval"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":56,"forksCount":13,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-13T11:10:51.086Z"}},{"type":"Public","name":"prophet","owner":"MILVLG","isFork":false,"description":"Implementation of CVPR 2023 paper \"Prompting Large Language Models with Answer Heuristics for Knowledge-based Visual Question Answering\".","allTopics":["pytorch","visual-question-answering","multimodal-deep-learning","gpt-3","prompt-engineering","okvqa","a-okvqa"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":261,"forksCount":27,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-23T01:12:22.406Z"}},{"type":"Public","name":"bst","owner":"MILVLG","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":5,"forksCount":1,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-12T13:34:13.760Z"}},{"type":"Public","name":"xmchat","owner":"MILVLG","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":3,"starsCount":30,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-04-24T14:26:43.695Z"}},{"type":"Public","name":"bottom-up-attention.pytorch","owner":"MILVLG","isFork":false,"description":"A PyTorch reimplementation of bottom-up-attention models","allTopics":["bottom-up-attention","detectron2","pytorch"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":24,"starsCount":289,"forksCount":75,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2022-04-07T13:37:56.081Z"}},{"type":"Public","name":"openvqa","owner":"MILVLG","isFork":false,"description":"A lightweight, scalable, and general framework for visual question answering research","allTopics":["benchmark","deep-learning","pytorch","vqa","visual-question-answering"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":6,"starsCount":311,"forksCount":64,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2021-09-03T12:54:09.615Z"}},{"type":"Public","name":"mcan-vqa","owner":"MILVLG","isFork":false,"description":"Deep Modular Co-Attention Networks for Visual Question Answering","allTopics":["attention","visual-reasoning","visual-question-answering"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":433,"forksCount":88,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-12-16T04:07:19.333Z"}},{"type":"Public","name":"activitynet-qa","owner":"MILVLG","isFork":false,"description":"An VideoQA dataset based on the videos from ActivityNet","allTopics":["vqa","activitynet","videoqa","dataset"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":57,"forksCount":9,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-11-22T03:00:54.776Z"}},{"type":"Public","name":"mmnas","owner":"MILVLG","isFork":false,"description":"Deep Multimodal Neural Architecture Search","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":26,"forksCount":8,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-11-15T06:19:29.128Z"}},{"type":"Public","name":"mt-captioning","owner":"MILVLG","isFork":false,"description":"A PyTorch implementation of the paper Multimodal Transformer with Multiview Visual Representation for Image Captioning","allTopics":["pytorch","image-captioning","multimodal-transformer"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":1,"starsCount":24,"forksCount":7,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2020-09-04T13:15:17.918Z"}}],"repositoryCount":14,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}