Training transformer-based encoder-decoder models for long document summarization poses a significant challenge due to the quadratic memory consumption during training. Several approaches have been proposed to extend the input length at test time, but training with these approaches is still difficult, requiring truncation of input documents and causing a mismatch between training and test conditions. In this work, we propose CachED (Gradient $\textbf{Cach}$ing for $\textbf{E}$ncoder-$\textbf{D}$ecoder models), an approach that enables end-to-end training of existing transformer-based encoder-decoder models, using the entire document without truncation. Specifically, we apply non-overlapping sliding windows to input documents, followed by fusion in decoder. During backpropagation, the gradients are cached at the decoder and are passed through the encoder in chunks by re-computing the hidden vectors, similar to gradient checkpointing. In the experiments on long document summarization, we extend BART to CachED BART, processing more than 500K tokens during training and achieving superior performance without using any additional parameters.

When Melissa Kono, the town clerk in Burnside, Wisconsin, began training election workers in 2015, their questions were relatively mundane. They asked about election rules, voter eligibility, and other basic procedures. The job was gratifying and enjoyable; they helped their neighbors while sipping coffee. But over the past few years, everything has changed. Kono now finds herself fielding questions about what to do when approached by suspicious voters who ask provocative questions or gripe about fraud.

EA Sports is getting a bad rap from a former soccer star for its rankings in its video game. Formerly known as "FIFA," "EA Sports FC" has included both men and women for users to play. However, Joey Barton noticed what he feels is a peculiar aspect of the game regarding the ratings of the game. Joey Barton of the Queens Park Rangers applauds the fans during the Sky Bet Championship playoff final match between Derby County and Queens Park Rangers at Wembley Stadium on May 24, 2014, in London. In any video game, obviously, the higher the rating, the better the players are, with 99 usually being the highest score.

Like many students around the world, Eithne, 14, in Chorley, United Kingdom, was struggling to keep up in math at school after more than a year of COVID-19 related disruptions. In June 2021, her parents signed her up for a summer program offered by Eedi, an online math tutoring service. "Just dealing with lockdown, she hadn't had enough of a really good background," said her mother, Arianna. "She missed most of the Year 7 Maths, then Year 8. So, we thought, 'Let's give it a go, let's see where she needs a bit of help.'" Newly enrolled students on Eedi are asked to take a dynamic quiz of 10 multiple choice diagnostic questions that the service uses to learn where students struggle most in math.

Like many students around the world, Eithne, 14, in Chorley, United Kingdom, was struggling to keep up in math at school after more than a year of COVID-19 related disruptions. In June 2021, her parents signed her up for a summer program offered by Eedi, an online math tutoring service. "Just dealing with lockdown, she hadn't had enough of a really good background," said her mother, Arianna. "She missed most of the Year 7 Maths, then Year 8. So, we thought, 'Let's give it a go, let's see where she needs a bit of help.'" Newly enrolled students on Eedi are asked to take a dynamic quiz of 10 multiple choice diagnostic questions that the service uses to learn where students struggle most in math. This information allows the service to place students on a learning pathway to overcome those specific obstacles, or misconceptions.

HARMI (Human and Robotic Musical Improvisation) is a software and hardware system that enables musical robots to improvise with human performers. The goal of the system is not to replicate human musicians, but rather to explore the novel kinds of musical expression that machines can produce. At the same time, the system seeks to create spaces where humans and robots can communicate with each other in a common language. To help achieve the former, ideas from contemporary compositional practice and music theory were used to shape the system's expressive capabilities. In regard to the latter, research from the field of cognitive psychology was incorporated to enable communication, interaction, and understanding between human and robotic performers. The system was partly developed in conjunction with a residency at High Concept Laboratories in Chicago, IL, where a group of human improvisers performed with the robotic instruments. The system represents an approach to the question of how humans and robots can interact and improvise in musical contexts. This approach purports to highlight the unique expressive spaces of humans, the unique expressive spaces of machines, and the shared spaces between the two.

The first quarter delivered home-sale profits that were more than twice as high as anticipated, the company said. Zillow expected to make money primarily from transaction fees and from services such as title insurance--not from making a killing on the flip. The company's algorithm, which was supposed to predict housing prices, didn't seem to understand the market. Zillow was also behind on its target for home purchases. By the summer, it had the opposite problem, the company later acknowledged.

Stories of people getting cash offers for their homes tens of thousands of dollars over asking price have become normal. This year, inventory in the US housing market hit a record low while home prices hit a record high. Redfin CEO Glenn Kelman recently highlighted the craziness with a tweet recounting the story of a home buyer who offered to name their first-born child after the seller--and was turned down. As the hot US housing market began to overheat, in February Zillow began making initial cash offers to buy homes based on its price estimate. Now Zillow has updated its algorithm behind those estimates in a way the company says will make them more accurate--and allow Zillow to offer to buy more homes.

Embedded in the narrative DNA of the new Netflix movie Stowaway is one of the most iconic and controversial science-fiction short stories ever published, "The Cold Equations," by Tom Godwin. Like "The Cold Equations," Stowaway is the story of a spaceship journey that hits a snag when an additional passenger is discovered onboard. The ship can't complete its trip with the extra drain on its resources, so somebody has to go out the airlock. "The Cold Equations" first appeared in the August 1954 edition of Astounding magazine, whose editor, John W. Campbell Jr., played a major role in defining the genre of "hard science fiction"--that is, stories fundamentally concerned with the accurate depiction of science and technology. According to legend, Campbell sent the story back to Godwin several times because the author kept trying to find a way for the characters to wriggle out of the story's central dilemma and achieve a happy ending.

Anyone who's been to a concert knows that something magical happens between the performers and their instruments. It transforms music from being just "notes on a page" to a satisfying experience. A University of Washington team wondered if artificial intelligence could recreate that delight using only visual cues--a silent, top-down video of someone playing the piano. The researchers used machine learning to create a system, called Audeo, that creates audio from silent piano performances. When the group tested the music Audeo created with music-recognition apps, such as SoundHound, the apps correctly identified the piece Audeo played about 86% of the time.