Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is based on three new ideas. First, we incorporate an inaccurate off-the-shelf depth estimator into 3D GAN training via a special depth adaptation module to handle the imprecision. Then, we create a flexible camera model and a regularization strategy for it to learn its distribution parameters during training. Finally, we extend the recent ideas of transferring knowledge from pre-trained classifiers into GANs for patch-wise trained models by employing a simple distillation-based technique on top of the discriminator. It achieves more stable training than the existing methods and speeds up the convergence by at least 40%. We explore our model on four datasets: SDIP Dogs 256x256, SDIP Elephants 256x256, LSUN Horses 256x256, and ImageNet 256x256, and demonstrate that 3DGP outperforms the recent state-of-the-art in terms of both texture and geometry quality. Code and visualizations: https://snap-research.github.io/3dgp.

Within the past few weeks, ChatGPT, a groundbreaking advancement in the field of artificial intelligence, has given unprecedented power to every Internet user. It's gained immense popularity, garnering one million users in just five days. OpenAI released this first-of-its-kind consumer-based AI product with endless abilities ranging from writing essays or writing code to building entire apps to passing professional-level tests. Chatbots have existed for decades, with ones such as Siri and Alexa acting as virtual assistants. They can execute quick searches such as "Will it rain tomorrow in Bologna?" or "What is 2 2?" ChatGPT has the unique capability to answer more abstract and open-ended questions with immense detail.

'Gutfeld!' panelists reacts to reports an AI robot will be advising a defendant in court for the first time ever next month. A software engineer who was fired by Google after he blew the whistle on the danger of artificial intelligence (AI) to the public has turned his attention to Microsoft's newest AI chatbot, Bing Search. On Monday, Lemoine targeted Microsoft's AI in an op-ed for Newsweek, calling the technology behind it "the most powerful technology that has been invented since the atomic bomb. In my view, this technology has the ability to reshape the world." Blake Lemoine first made headlines in 2022 after he claimed that Google's AI chatbot was becoming sentient, and might even have a soul.

Generative artificial intelligence is currently one of the hottest topics in Silicon Valley, and its impact is already being felt in the music industry. BandLab -- the music-creation app that has become popular on TikTok -- relies on AI as the engine for its tool SongStarter. Users can lean on it to generate beats or melodies at random, or prompt it to spit something out based on specific lyrics and emojis; BandLab's 60 million registered creators are churning out more than 17 million songs each month, including breakout hits for dv4d and ThxSoMch. The tracks that emerge from BandLab depend on the interaction of human creators and AI. That holds true for some of the companies focusing on functional audio as well.

As a child of the '80s, I can divide my life cleanly into Before Google and After Google. Right around the turn of the millennium, the internet stopped being a tangled thicket of incomplete lists of weird stuff and became a useful research database. Ever since, Google Search has been one of the only technological constants of my adult life, persisting through the rise of smartphones, social media, streaming services, and even drone-based burrito delivery (also, what happened to that?). In all that time, nobody has been able to challenge Google's role as gatekeeper to the cornucopia of digital abundance. More than 90 percent of internet users around the world use Google to shop, navigate, and satisfy their curiosity about pretty much everything.

The rise of AI technology has brought about many changes in various industries, and photography is no exception. With AI photography, the line between what is real and what is fake has become increasingly blurred. This has sparked a debate on the significance of authenticity in photography and the impact that AI technology has on the art form. Artificial intelligence is being used to enhance photos, manipulate images, and even create entirely new images from scratch. This technology can produce highly realistic images, making it difficult to distinguish between what was captured in a camera and what was created in a computer. While AI photography has the potential to revolutionize the industry and open up new possibilities for artists, it also raises questions about the ethics of using AI in photography.

Science fiction stories and movies have been predicting what the world to come would look like for decades. Remember Spock asking questions to Star Trek's version of Alexa almost 60 years ago? Scottie probably could have utilized Alexa to warn him before he needed more dilithium crystals. Personally, I think the Enterprise was always running low on power because they switched from fusion matter-antimatter dilithium reactor technology to the Green New Deal. Michael Ramirez Newsletter is a reader-supported publication.

Google researchers have introduced MusicLM, an AI model that can generate high-fidelity music from text. MusicLM creates music at a constant 24 kHz throughout a number of minutes by modeling the conditional music generating process as a hierarchical sequence-to-sequence modeling problem. According to the research paper, MusicLM was trained on a dataset of 280,000 hours of music to produce songs that make sense for complex descriptions. The researchers also claim their model outperforms previous systems both in audio quality and adherence to the text description. MusicLM samples, includes five-minute pieces produced from only one or two words like melodic techno, as well as 30-second samples that sound like entire songs and are formed from paragraph-long descriptions that prescribe a genre, vibe, and even specific instruments.

Knowing how to talk to chatbots may get you hired as a prompt engineer for generative AI. Prompt engineers are experts in asking AI chatbots -- which run on large language models -- questions that can produce desired responses. Unlike traditional computer engineers who code, prompt engineers write prose to test AI systems for quirks; experts in generative AI told The Washington Post that this is required to develop and improve human-machine interaction models. Alex Shoop, an expert in AI systems design, told Venture Beat that as AI tools evolve, prompt engineers help ensure that chatbots are rigorously tested, that their responses are reproducible, and that safety protocols are followed. The rise of the prompt engineer comes as chatbots like OpenAI's ChatGPT have taken the world by storm.

UNITED24 and Monobank have partnered with actor Mark Hamill to launch a fundraising campaign with the aim of collecting funds to help Ukraine purchase drones to use in the war against Russia. The fundraising campaign will send out 500 packs of unique iodized salt from the state-owned company Artemsil, which will be raffling off the prize among those who contribute at least UAH 10 ($0.27) or more. The first 100 participants who contribute at least UAH 100,000 ($2,701) will receive a salt pack signed by the commander of the ground forces of the Armed Forces of Ukraine Oleksandr Syrskyi. Another 10 packs of salt will also be signed by Hamill, the ambassador for UNITED24 and an actor well-known for his role as Luke Skywalker in the Star Wars saga, according to a press release. The project aims to raise UAH 59.2 million ($1.6 million) for Ukraine to purchase 300 DJI Mavic 3T Thermal drones.