Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Memberships

Prompt Monkey

Public • 409 • Free

49 contributions to Prompt Monkey
Understanding the visual knowledge of language models
LLMs trained primarily on text can generate complex visual concepts through code with self-correction. Researchers used these illustrations to train an image-free computer vision system to recognize real photos. You’ve likely heard that a picture is worth a thousand words, but can a large language model (LLM) get the picture if it’s never seen images before?As it turns out, language models that are trained purely on text have a solid understanding of the visual world. They can write image-rendering code to generate complex scenes with intriguing objects and compositions — and even when that knowledge is not used properly, LLMs can refine their images. Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) observed this when prompting language models to self-correct their code for different images, where the systems improved on their simple clipart drawings with each query.https://news.mit.edu/2024/understanding-visual-knowledge-language-models-0617
6
0
Oral-History:Robotics History: Narratives and Networks
Beginning in 2010, the IEEE Robotics and Automation Society, together with the School of Informatics and Computer Science at Indiana University, undertook a major robotics history project, “Robotics History: Narratives and Networks." Selma Šabanović of Indiana University was the principal investigator and led the project team. One of the major goals of the project was to document the development of robotics as a scientific field through an extensive program of oral histories with major figures in the field. More than one hundred oral histories were completed between 2010 and 2015. These oral histories are being posted here as they become available https://ethw.org/Oral-History:Robotics_History:_Narratives_and_Networks
6
0
Robots
Tool: Copilot
5
1
New comment May 31
Robots
5 AI Image Prompt Generators That Will Change Your Art Forever
GravityWrite: Best for creating detailed image prompts from your ideas. PromptoMANIA: Provides simple tools for generating AI-driven image prompts. AI Text Prompt Generator: Quickly crafts prompts for unique artwork. PromptHero: Offers a wide range of art prompts for AI generators. PromptPerfect: Fine-tune your prompts for enhanced text and image results. Details:https://gravitywrite.com/blog/best-ai-image-prompt-generators
6
0
20 Captivating AI Image Prompts!
Looking for some fun and unusual AI art prompt inspiration? Check out this list! Details: https://medium.com/@mericreativAI/20-captivating-ai-image-prompts-for-creative-minds-9f7d195b3fbd
6
0
1-10 of 49
Mehmet Güner
5
313points to level up
@mehmet-guner-7870
LLM & Generative AI Researcher

Active 106d ago
Joined May 10, 2024
Turkey
powered by