A new machine learning method attempts to account for biases that may be held by certain subsets of labelers.

Robots trained via reinforcement learning usually study videos of robots performing the task at hand. A new approach used videos of humans to pre-train robotic arms.

You can reduce your model’s carbon emissions by being choosy about when and where you train it.

A homebrew re-creation of OpenAI’s DALL·E model is the latest internet sensation. Craiyon has been generating around 50,000 user-prompted images daily, thanks to its ability to produce visual mashups like Darth Vader ice fishing and photorealistic Pokemon characters.

Transformers can learn a lot from sequential data like words in a book, but they’ve shown limited ability to learn from data in the form of a graph. A new transformer variant gives graphs due attention.

Adding layers to a neural network puts the “deep” in deep learning, but it also increases the chance that the network will get stuck during training. A new approach effectively trains transformers with an order of magnitude more layers than previous methods.

A new benchmark aims to raise the bar for large language models. Researchers at 132 institutions worldwide introduced the Beyond the Imitation Game benchmark (BIG-bench), which includes tasks that humans perform well but current state-of-the-art models don’t.

A chatbot persuaded at least one person that it has feelings. A senior engineer at Google announced his belief that the company’s latest conversational language model is sentient.

OpenAI’s text-to-image generator DALL·E 2 produces pictures with uncanny creativity on demand. Has it invented its own language as well? Ask DALL·E 2 to generate an image that includes text, and often its output will include seemingly random characters.

AI startups are helping writers tailor articles that appear near the top of Google’s search results. At least 14 companies sell access to software that uses GPT-3, the language model from OpenAI, to generate headlines, product descriptions, blog posts, and video scripts.

Let’s get this out of the way: A brain is not a cluster of graphics processing units, and if it were, it would run software far more complex than the typical artificial neural network. Yet neural networks were inspired by the brain’s architecture.

Researchers took a step toward achieving a longstanding goal: One model that performs a whole lot of very different tasks. Scott Reed, Konrad Żołna, Emilio Parisotto and a team at DeepMind announced Gato.

Vision Transformer and models like it use a lot of computation and memory when processing images. New work modifies these architectures to run more efficiently while adopting helpful properties from convolutions.

Itching to get your hands on a fully trained large language model? The wait is over. Meta introduced the OPT family of transformer-based language models with nearly unfettered access to source code and trained weights.

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.