“Nous avons demandé à trois Intelligences Artificielles (DALL.E, MIDJOUNEY & STABLE DIFFUSION) de générer des images. Laurence DEVILLER, Professeure en informatique et IA à la Sorbonne Université, et Albertine MEUNIER, Artiste Numérique et Chevalier de la Légion, d’Honneur-sauront elles les différencier d’oeuvres humaines ?”
“DALL·E’s Edit feature already enables changes within a generated or uploaded image — a capability known as Inpainting. Now, with Outpainting, users can extend the original image, creating large-scale images in any aspect ratio. Outpainting takes into account the image’s existing visual elements — including shadows, reflections, and textures — to maintain the context of the original image.”
“As part of Intel’s Responsible AI work, the company has productized FakeCatcher, a technology that can detect fake videos with a 96% accuracy rate. Intel’s deepfake detection platform is the world’s first real-time deepfake detector that returns results in milliseconds.
Most deep learning-based detectors look at raw data to try to find signs of inauthenticity and identify what is wrong with a video. In contrast, FakeCatcher looks for authentic clues in real videos, by assessing what makes us human— subtle “blood flow” in the pixels of a video. When our hearts pump blood, our veins change color. These blood flow signals are collected from all over the face and algorithms translate these signals into spatiotemporal maps. Then, using deep learning, we can instantly detect whether a video is real or fake. ”
“When the first instant photo was taken 75 years ago with a Polaroid camera, it was groundbreaking to rapidly capture the 3D world in a realistic 2D image. Today, AI researchers are working on the opposite: turning a collection of still images into a digital 3D scene in a matter of seconds. Known as inverse rendering, the process uses AI to approximate how light behaves in the real world, enabling researchers to reconstruct a 3D scene from a handful of 2D images taken at different angles. The NVIDIA Research team has developed an approach that accomplishes this task almost instantly — making it one of the first models of its kind to combine ultra-fast neural network training and rapid rendering.”
“Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the development of a deep learning model by clinicians without coding, which predicts reported sex from retinal fundus photographs. A model was trained on 84,743 retinal fundus photos from the UK Biobank dataset. External validation was performed on 252 fundus photos from a tertiary ophthalmic referral center.”
“There have been several AI breakthroughs to-date, including AI agents that have mastered arcade games, complex strategy games such as chess, shogi and Go as well as other real-time, multiplayer strategy games. GT Sophy takes game AI to the next level, tackling the challenge of a hyper-realistic simulator by mastering real-time control of vehicles with complex dynamics, all while operating within inches of opponents.”
“Which Face Is Real has been developed by Jevin West and Carl Bergstrom at the University of Washington as part of the Calling Bullshit project. All images are either computer-generated from thispersondoesnotexist.com using the StyleGAN software, or real photographs from the FFHQ dataset of Creative Commons and public domain images. License rights notwithstanding, we will gladly respect any requests to remove specific images; please send the URL of the results pages showing the image in question.”
“Harness the power of AI to quickly turn simple brushstrokes into realistic landscape images for backgrounds, concept exploration, or creative inspiration. 🖌️ The NVIDIA Canvas app lets you create as quickly as you can imagine.”
“This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology. It has occurred decades before many people in the field would have predicted. It will be exciting to see the many ways in which it will fundamentally change biological research”.
Professor Venki Ramakrishnan – Nobel Laureate and President of the Royal Society
“We trained this system on publicly available data consisting of ~170,000 protein structures from the protein data bank together with large databases containing protein sequences of unknown structure. It uses approximately 16 TPUv3s (which is 128 TPUv3 cores or roughly equivalent to ~100-200 GPUs) run over a few weeks, a relatively modest amount of compute in the context of most large state-of-the-art models used in machine learning today.”