Summary GigaGAN shows that Generative Adversarial Networks are far from obsolete and could be a faster alternative to Stable Diffusion in the future. Current generative AI models for images are diffusion models trained on large datasets that generate images based on text descriptions. They have replaced GANs (Generative Adversarial Network), which were widely used in …
An old AI architecture shows off some new tricks Read More »
Summary Metas DINOv2 is a foundation model for computer vision. The company shows its strengths and wants to combine DINOv2 with large language models. In May 2021, AI researchers at Meta presented DINO (Self-Distillation with no labels), a self-supervised trained AI model for image tasks such as classification or segmentation. With DINOv2, Meta is now …
Metas DINOv2 is a foundation model for computer vision Read More »
Summary Instruct-NeRF2NeRF uses methods of generative AI models and can edit 3D scenes according to text input. Earlier this year, researchers at the University of California Berkeley demonstrated InstructPix2Pix, a method that allows users to edit images in Stable Diffusion using text instructions. The method makes it possible to replace objects in images or change …
Instruct-NeRF2NeRF lets you edit NeRFs via text prompt Read More »
Summary People take photos for many reasons, one of which is to capture memories. The next generation of keepsake photos may be NeRFs, which get a quality upgrade at high speed with Zip-NeRF. Google researchers demonstrate Zip-NeRF, a NeRF model that combines the advantages of grid-based techniques and the Mipmap-based mip-NeRF 360. Grid-based NeRF methods, …
Zip-NeRF is another step towards a digital time machine Read More »
Newsletter In recent years, the potential progress of large language models has been measured primarily by the number of parameters. Sam Altman, CEO of OpenAI, believes that this practice is no longer useful. Altman compares the race to increase the number of parameters in large language models to the race to increase the clock speed …
OpenAI CEO sees ‘end of an era’ in number of parameters Read More »
Summary Microsoft researchers see a spark of general AI in an early version of GPT-4. “We believe that GPT-4’s intelligence signals a true paradigm shift in the field of computer science and beyond,” says the paper released by Microsoft. GPT-4 shows a spark of general artificial intelligence (AGI), they say, but is only the first …
Summary Google and Deepmind are working together to develop a GPT-4 competitor called “Gemini”. The Information reports that the Google Brain AI team is working with Deepmind on an alternative to OpenAI’s GPT-4. Work on the Gemini project is said to have begun in recent weeks after Google’s Bard failed to keep up with ChatGPT. …
Summary Stanford’s Alpaca was just the beginning: In recent weeks, several AI models have been unveiled using training data generated by ChatGPT. In mid-March, Stanford researchers unveiled the Alpaca language model, a variant of Meta’s LLaMA 7B that was fine-tuned with AI-generated data. The team trained the LLaMA model with 52,000 example statements generated by …
Summary After Alpaca comes Vicuna, an open-source chatbot that, according to its developers, is even closer to ChatGPT’s performance. Vicuna follows the “Alpaca formula” and uses ChatGPT’s output to fine-tune a large language model from Metas LLaMA family. The team behind Vicuna includes researchers from UC Berkeley, CMU, Stanford, and UC San Diego. While Alpaca …
GPT-4 likes this chatbot almost as much as ChatGPT Read More »
Summary PAC-NeRF demonstrates how NeRFs can learn the geometric structure and physical properties of objects from video. Neural radiance fields (NeRFs) are a powerful AI-based rendering technology that can be used for video production, 3D reconstruction, and other tasks. They learn to represent and render the geometric structure and lighting of scenes and objects from …
PAC-NeRF learns physical properties of objects from videos Read More »
