Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and robustness. Inspired by ResNet's residual learning, we propose Residual Mixture-of-Agents (RMoA), integrating residual connections to optimize efficiency and reliability. To maximize information utilization from model responses while minimizing computational costs, we innovatively design an embedding-based diversity selection mechanism that greedily selects responses via vector similarity. Furthermore, to mitigate iterative information degradation, we introduce a Residual Extraction Agent to preserve cross-layer incremental information by capturing inter-layer response differences, coupled with a Residual Aggregation Agent for hierarchical information integration. Additionally, we propose an adaptive termination mechanism that dynamically halts processing based on residual convergence, further improving inference efficiency. RMoA achieves state-of-the-art performance on the benchmarks of across alignment, mathematical reasoning, code generation, and multitasking understanding, while significantly reducing computational overhead. Code is available at https://github.com/mindhunter01/RMoA.

Netflix researchers have created a new type of AI-powered green-screen technology that can produce realistic visual effects for film and television in real time. Green-screen technology is routinely used to capture footage of actors that can then be inserted in the foreground of virtual or prerecorded scenes. To do this, actors are filmed against a bright green background, which is easily isolated and removed digitally. This process can be done automatically with reasonable accuracy, such as in television weather forecasts, but it can be thrown by items of green clothing or by transparent or fine objects, like wisps of hair. When greater accuracy is needed in films or television series, specialist operators tweak settings manually, sometimes requiring hours to perfect a shot.

Kim Libreri, an award-winning visual effects artist based in Northern California, has worked on movies including Artificial Intelligence and War of the Planet of the Apes. For nine years he has been working with a piece of technology better known for computer games, in particular the smash-hit Fortnite. The Unreal Engine, owned by Epic Games, provides the building blocks and tools that a computer game developer needs, but is increasingly an attractive technology for TV and film producers. The latest version of technology, Unreal Engine 5, is coming out next year, and Epic has been heavily trailing its features. It should allow visual effects artists like Mr Libreri to slot graphics and images straight into a scene, with little fuss.

Around the time Leonardo Da Vinci was painting the Mona Lisa, he was also writing his Codex on the Flight of Birds, a roughly 35,000-word exploration of the ways in which man might take to the air. His illustrations included diagrams positing pre-Newtonian theories of physics, a rudimentary plan for a flying machine and many, many sketches of birds in flight. The Mona Lisa, with her secretive smile, is a universe of intimacy captured on a relatively small panel of wood. But the landscape behind his captivating subject shows the world as you would see it from atop a tall hill--or from the vantage point you would get if you had hitched a ride on the back of a giant bird. Even as da Vinci was perfecting one way of seeing a face, he was dreaming of other ways of looking.

In his 2014 book, No Place to Hide, Glenn Greenwald wrote that a contributing factor to Edward Snowden's decision to leak classified information from the NSA was his consumption of video games: "The moral narrative at the heart of video games was part of his pre-adolescence and formed part of his moral understanding of the world and one's obligation as an individual." Whether or not you agree with Snowden's actions, the idea that playing video games could affect a person's ethical position or even encourage any kind of philosophical thought is probably surprising. Yet we're used to the notion that a person's thinking could be influenced by the characters and conundrums in books, film and television; why not games? In fact, games have one big advantage that makes them especially useful for exploring philosophical ideas: they're interactive. As any student of philosophy will tell you, one of the primary ways of engaging with abstract questions is through thought experiments.

Over recent years, we've seen artificial intelligence systems designed to write software, compose music, paint works of art, and even pen news articles, but the machines have been notably quiet in the medium of fiction storytelling. Designing an A.I. system that can write the screenplay for a movie, or compose a great novel, has posed a big challenge for researchers. So just how close are we to having machines pen our blockbuster films? In June, a bizarre short film entitled Sunspring premiered. Filled with incoherent non-sequiturs and inexplicably surreal tangents, the film could be considered either a compelling dream-like fugue or an amateurish mess.

Managing large collections of documents is an important problem for many areas of science, industry, and culture. Probabilistic topic modeling offers a promising solution. Topic modeling is an unsupervised machine learning method that learns the underlying themes in a large collection of otherwise unorganized documents. This discovered structure summarizes and organizes the documents. However, topic models are high-level statistical tools—a user must scrutinize numerical distributions to understand and explore their results. In this paper, we present a method for visualizing topic models. Our method creates a navigator of the documents, allowing users to explore the hidden structure that a topic model discovers. These browsing interfaces reveal meaningful patterns in a collection, helping end-users explore and understand its contents in new ways. We provide open source software of our method.