Lifeboat Foundation

A team of computer programmers at IT University of Copenhagen has developed a new way to encode and generate Super Mario Bros. levels—called MarioGPT, the new approach is based on the language model GPT-2. The group outlines their work and the means by which others can use their system in a paper on the arXiv pre-print server.

Mario Brothers is a video game first introduced in 1983—it involves two Italian plumbers emerging from a sewer and attempting to rescue Princess Peach, who has been captured and held by Bowser. To rescue her, the brothers must travel (via input from the game player) across a series of obstacles made of pipes and bricks. As they travel, the terrain changes in accordance with the level they have achieved in the game. In this new effort, the team in Denmark has recreated one aspect of the game—the number of levels that can be traversed.

The researchers used Generative Pre-trained Transformer 2 (GPT-2)—an open-source language model created by a team at OpenAI, to translate user requests into graphical representations of Super Mario Brothers game levels. To do so, they created a small bit of Python code to help the language model understand what needed to be done and then trained it using samples from the original Super Mario Bros. game and one of its sequels, “Super Mario Bros.: The Lost Levels.”

Inside the mall, customers’ avatars will find Carrefour, VOX Cinemas, THAT Concept Store, Ghawali and Samsung Store, “with many more brands and exciting features in the pipeline”.

Announced at the World Government Summit, the mall is in the initial phase of development as the group looks “closely” at customers’ needs and expectations.

Khalifa bin Braik, CEO of Majid Al Futtaim Asset Management, said the Mall of the Metaverse will be a leading retail and entertainment destination — “and surely a huge attraction for customers who crave digital experiences from their most loved brands”.

Summary: Tracking hippocampal neurons in mice as they watched a movie revealed novel ways to improve artificial intelligence and track neurological disorders associated with memory and learning deficits.

Source: UCLA

Even the legendary filmmaker Orson Welles couldn’t have imagined such a plot twist.

Science fiction films love to show off huge leaps in technology. The latest Avatar movie features autonomous, spider-like robots that can build a whole city within weeks. There are space ships that can carry frozen passengers lightyears away from Earth. In James Cameron’s imagination, we can download our memories and then upload them into newly baked bodies. All this wildly advanced tech is controlled through touch-activated, transparent, monochrome and often blue holograms. Just like a thousand other futuristic interfaces in Hollywood.

When we are shown a glimpse of the far future through science fiction films, there are omnipresent voice assistants, otherworldly wearables, and a whole lot of holograms. For whatever reason these holograms are almost always blue, floating above desks and visible to anyone who might stroll by. This formula for futuristic UI has always baffled me, because as cool as it looks, it doesn’t seem super practical. And yet, Hollywood seems to have an obsession with imagining future worlds washed in blue light.

Continue reading “Why all of Hollywood UI looks the same” »

1920s Startrek TOS Series

Let’s imagine what current movies/series would be like in 1920…//

The current media environment is filled with visual effects and video editing. As a result, as video-centric platforms have gained popularity, demand for more user-friendly and effective video editing tools has skyrocketed. However, because video data is temporal, editing in the format is still difficult and time-consuming. Modern machine learning models have shown considerable promise in enhancing editing, although techniques frequently compromise spatial detail and temporal consistency. The emergence of potent diffusion models trained on huge datasets recently caused a sharp increase in the quality and popularity of generative techniques for picture synthesis. Simple users may produce detailed pictures using text-conditioned models like DALL-E 2 and Stable Diffusion with only a text prompt as input. Latent diffusion models effectively synthesize pictures in a perceptually constrained environment. They research generative models suitable for interactive applications in video editing due to the development of diffusion models in picture synthesis. Current techniques either propagate adjustments using methodologies that calculate direct correspondences or, by finetuning on each unique video, re-pose existing picture models.

They try to avoid costly per-movie training and correspondence calculations for quick inference for every video. They suggest a content-aware video diffusion model with a configurable structure trained on a sizable dataset of paired text-image data and uncaptioned movies. They use monocular depth estimations to represent structure and pre-trained neural networks to anticipate embeddings to represent content. Their method gives several potent controls on the creative process. They first train their model, much like image synthesis models, so the inferred films’ content, such as their look or style, correspond to user-provided pictures or text cues (Fig. 1).

Figure 1: Video Synthesis With Guidance We introduce a method based on latent video diffusion models that synthesises videos (top and bottom) directed by text-or image-described content while preserving the original video’s structure (middle).

There’s a lot about ecology in frank Herbert’s dune saga and eco mysticism as well.

I will never make any money from Youtube and that is perfectly correct!
I will always get this message: “Your video is ineligible for monetization due to a copyright claim.“
And: “Ad revenue paid to copyright owner”

Continue reading “Iron Maiden — To tame a land (Lyrics included)” »

Annotation and analysis of sports videos is a time-consuming task that, once automated, will provide benefits to coaches, players, and spectators. American football, as the most watched sport in the United States, could especially benefit from this automation. Manual annotation and analysis of recorded videos of American football games is an inefficient and tedious process. Currently, most college football programs focus on annotating offensive formations to help them develop game plans for their upcoming games. As a first step to further research for this unique application, we use computer vision and deep learning to analyze an overhead image of a football play immediately before the play begins. This analysis consists of locating individual football players and labeling their position or roles, as well as identifying the formation of the offensive team.

Deepfake technology has been around for some time, and it’s currently causing controversies for the potential threats it may bring when fallen into the wrong hands. Even India’s business tycoon Anand Mahindra sparked alarm over hyper-realistic synthetic videos.

But some personalities are redefining the way viewers perceive deepfakes. For instance, David Guetta recently synthesized Eminem’s voice to hype up an event. And it’s only one of the many examples of people using artificial intelligence (AI) for entertainment. In fact, it already came to different social media websites like Twitch that take streaming to the next level.

Bachir Boumaaza is a Youtuber who once made a name for his record-breaking games, which he used to help numerous charities. But he became inactive, with most of his fans wondering where he went, thinking it might’ve been the end of his career.