{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"SEED-X","owner":"AILab-CVC","isFork":false,"description":"Multimodal Models in Real World","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":5,"starsCount":266,"forksCount":11,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-29T11:11:14.500Z"}},{"type":"Public","name":"SEED-Bench","owner":"AILab-CVC","isFork":false,"description":"(CVPR2024)A benchmark for evaluating Multimodal LLMs using multiple-choice questions.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":18,"starsCount":259,"forksCount":8,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-29T10:32:45.288Z"}},{"type":"Public","name":"CV-VAE","owner":"AILab-CVC","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-29T08:52:47.668Z"}},{"type":"Public","name":"YOLO-World","owner":"AILab-CVC","isFork":false,"description":"[CVPR 2024] Real-Time Open-Vocabulary Object Detection","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":176,"starsCount":3625,"forksCount":345,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-20T03:58:08.704Z"}},{"type":"Public","name":"VideoCrafter","owner":"AILab-CVC","isFork":false,"description":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","allTopics":["video-generation","image-to-video","text-to-video"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":47,"starsCount":4171,"forksCount":308,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T06:20:43.710Z"}},{"type":"Public","name":"SEED","owner":"AILab-CVC","isFork":false,"description":"Official implementation of SEED-LLaMA (ICLR 2024).","allTopics":["multimodal","vision-language","foundation-model"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":23,"starsCount":496,"forksCount":27,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-11T12:46:51.189Z"}},{"type":"Public","name":"HiFi-123","owner":"AILab-CVC","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":42,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-04T10:55:51.515Z"}},{"type":"Public","name":"AILab-CVC.github.io","owner":"AILab-CVC","isFork":false,"description":"Homepage of Tencent AI Lab CVC.","allTopics":[],"primaryLanguage":{"name":"HTML","color":"#e34c26"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-28T03:17:47.112Z"}},{"type":"Public","name":"TaleCrafter","owner":"AILab-CVC","isFork":false,"description":"[SIGGRAPH Asia 2023] An interactive story visualization tool that support multiple characters","allTopics":["storytelling","storycreation","siggraph-asia-2023","siggprah-asia"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":5,"starsCount":241,"forksCount":13,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-22T11:53:35.885Z"}},{"type":"Public","name":"M2PT","owner":"AILab-CVC","isFork":false,"description":"[CVPR'24] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities","allTopics":["deep-learning","transformers","artificial-intelligence","multimodal"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":71,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-13T06:28:04.321Z"}},{"type":"Public","name":"Make-Your-Video","owner":"AILab-CVC","isFork":false,"description":"[IEEE TVCG 2024] Customized Video Generation Using Textual and Structural Guidance","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":166,"forksCount":7,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-24T07:56:41.852Z"}},{"type":"Public","name":"Animate-A-Story","owner":"AILab-CVC","isFork":false,"description":"Retrieval-Augmented Video Generation for Telling a Story ","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":3,"starsCount":240,"forksCount":17,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-05T15:07:35.183Z"}},{"type":"Public","name":"FreeNoise","owner":"AILab-CVC","isFork":false,"description":"[ICLR 2024] Code for FreeNoise based on VideoCrafter","allTopics":["generative-model","diffusion","aigc","video-diffusion-model"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":6,"starsCount":333,"forksCount":24,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-31T08:37:37.334Z"}},{"type":"Public","name":"UniRepLKNet","owner":"AILab-CVC","isFork":false,"description":"[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","allTopics":["deep-learning","architecture","artificial-intelligence","convolutional-neural-networks","multimodal-learning"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":834,"forksCount":52,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-02T18:17:46.777Z"}},{"type":"Public","name":"GPT4Tools","owner":"AILab-CVC","isFork":false,"description":"GPT4Tools is an intelligent system that can automatically decide, control, and utilize different visual foundation models, allowing the user to interact with images during a conversation.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":14,"starsCount":732,"forksCount":54,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-19T01:55:15.585Z"}},{"type":"Public","name":"VL-GPT","owner":"AILab-CVC","isFork":false,"description":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":2,"starsCount":83,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-15T15:01:21.171Z"}},{"type":"Public","name":"GroupMixFormer","owner":"AILab-CVC","isFork":false,"description":"GroupMixAttention and GroupMixFormer","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":107,"forksCount":11,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-13T05:07:44.494Z"}}],"repositoryCount":17,"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"}