{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"Video-ChatGPT","owner":"mbzuai-oryx","isFork":false,"description":"[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.","topicNames":["chatbot","llama","clip","mulit-modal","vision-language","vicuna","gpt-4","vision-language-pretraining","llava","video-chatboat"],"topicsNotShown":1,"allTopics":["chatbot","llama","clip","mulit-modal","vision-language","vicuna","gpt-4","vision-language-pretraining","llava","video-chatboat","video-conversation"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":8,"starsCount":980,"forksCount":87,"license":"Creative Commons Attribution 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-20T07:38:29.262Z"}},{"type":"Public","name":"CVRR-Evaluation-Suite","owner":"mbzuai-oryx","isFork":false,"description":"Official repository of paper titled \"How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs\".","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":31,"forksCount":1,"license":"Creative Commons Attribution 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-13T08:12:19.411Z"}},{"type":"Public","name":"LLaVA-pp","owner":"mbzuai-oryx","isFork":false,"description":"🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)","topicNames":["conversation","lmms","vision-language","llm","llava","llama3","phi3","llava-llama3","llava-phi3","llama3-llava"],"topicsNotShown":7,"allTopics":["conversation","lmms","vision-language","llm","llava","llama3","phi3","llava-llama3","llava-phi3","llama3-llava","phi3-llava","llama-3-vision","phi3-vision","llama-3-llava","phi-3-llava","llama3-vision","phi-3-vision"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":13,"starsCount":669,"forksCount":44,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-03T19:54:54.758Z"}},{"type":"Public","name":"groundingLMM","owner":"mbzuai-oryx","isFork":false,"description":"[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.","topicNames":["vision-and-language","lmm","foundation-models","vision-language-model","llm-agent"],"topicsNotShown":0,"allTopics":["vision-and-language","lmm","foundation-models","vision-language-model","llm-agent"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":10,"starsCount":593,"forksCount":28,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-15T13:00:04.620Z"}},{"type":"Public","name":"PALO","owner":"mbzuai-oryx","isFork":false,"description":"Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, Hindi, Bengali and Urdu.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":72,"forksCount":3,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-26T10:32:02.722Z"}},{"type":"Public","name":"GeoChat","owner":"mbzuai-oryx","isFork":false,"description":"[CVPR 2024 🔥] GeoChat, the first grounded Large Vision Language Model for Remote Sensing","topicNames":["remote-sensing","vlm"],"topicsNotShown":0,"allTopics":["remote-sensing","vlm"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":18,"starsCount":298,"forksCount":17,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-24T15:54:57.766Z"}},{"type":"Public","name":"BiMediX","owner":"mbzuai-oryx","isFork":false,"description":"Bilingual Medical Mixture of Experts LLM","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":1,"starsCount":22,"forksCount":1,"license":"Other","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,25,1,0,0,5,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-17T11:22:28.420Z"}},{"type":"Public","name":"MobiLlama","owner":"mbzuai-oryx","isFork":false,"description":"MobiLlama : Small Language Model tailored for edge devices","topicNames":["slm","llm","efficient-llm","mobile-llm","tiny-llm"],"topicsNotShown":0,"allTopics":["slm","llm","efficient-llm","mobile-llm","tiny-llm"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":10,"starsCount":537,"forksCount":38,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-03T22:04:01.419Z"}},{"type":"Public","name":"ClimateGPT","owner":"mbzuai-oryx","isFork":false,"description":"[EMNLP'23] ClimateGPT: a specialized LLM for conversations related to Climate Change and Sustainability topics in both English and Arabic languages.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":69,"forksCount":9,"license":null,"participation":[2,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,1,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-30T17:04:52.501Z"}},{"type":"Public","name":"Video-LLaVA","owner":"mbzuai-oryx","isFork":false,"description":"PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models","topicNames":["video","transcription","lmm","grounding","video-grounding","llm","video-conversation"],"topicsNotShown":0,"allTopics":["video","transcription","lmm","grounding","video-grounding","llm","video-conversation"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":14,"starsCount":206,"forksCount":12,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-02T17:51:01.418Z"}},{"type":"Public","name":"XrayGPT","owner":"mbzuai-oryx","isFork":false,"description":"XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":13,"starsCount":430,"forksCount":51,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-05T14:25:34.529Z"}},{"type":"Public","name":"Awesome-CV-Foundational-Models","owner":"mbzuai-oryx","isFork":true,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":7,"forksCount":23,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-31T11:27:15.148Z"}}],"repositoryCount":12,"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"}