14 Nov 2023
Dive into the realm where AI merges sight and language! 🌐👁️
Check out "CogVLM: Visual Expert for Pretrained Language Models," a paper that innovates in blending text and image understanding. This model, CogVLM-17B, introduces a new approach with deep fusion between visual and language information, overcoming the limitations of existing VLMs.
🔍 Read the full paper here: arxiv.org/abs/2311.03079
#AIResearch #VisualLanguageModel #CogVLM #InnovationInAI
What potential do you see in AI that understands both text and images deeply? Let's discuss the future of multimodal AI! 🤖🖼️💬
3
198
NSFW画像
(画像は省略します)
Prompt:
What's in this image? answer in japanese and 3 lines.
APIからのレスポンスメッセージ:
(エラーが返ってきました。引き続きNSFWはダメみたいですね)
NSFW投げれるVisualLanguageModelどこですか？
OpenAIのgpt-4-vision-previewに画像を投げてどんなことをしてくれるのか試してみた｜ねぎぽよし @CST_negi note.com/negipoyoc/n/n5587ee… #note
写真から想定される危険を論じさせたり、サイゼの間違い探しを解かせたり、色々試してみました
2
665
26 May 2023
The impressive visual language model, Flamingo, is revolutionizing the way individuals can engage with @YouTube Shorts. 🦩
With its ability to:
1️⃣ Automatically craft descriptions for countless videos based on their metadata.
2️⃣ Enhance video searchability.
Discover how AI is benefiting both creators and viewers. ⬇️
#Flamingo #VisualLanguageModel #YouTubeShorts #AI
5
214
Through millions of repetitions, it could discover not just the patterns among the words, but the relationships between the words and the elements the image
#artificialintelligence #ai #visuallanguagemodel #machinelearning #deeplearning #neuralnetworks
technologyreview.com/2020/09…