Day: January 9, 2024

Mercedes-Benz’s best-in-class voice assistant is getting an AI boost

Mercedes-Benz is introducing generative AI to enhance its in-car voice assistant, creating a more human-like and personalized experience for drivers. The upgraded MBUX Virtual Assistant will run on the next-generation MB.OS operating system, offering features such as predictive behavior and personalized responses. The company aims to provide natural interactions and minimize distractions for drivers. Mercedes-Benz […]

Regulators aren’t convinced that Microsoft and OpenAI operate independently

European Union regulators and other competition authorities are investigating Microsoft’s investment in OpenAI over concerns that Microsoft may be exerting control over OpenAI, potentially leading to distorted market dynamics and harmful competition behavior.   The investigations are prompted by governance changes at OpenAI, including the brief ousting and reappointment of CEO Sam Altman, and Microsoft’s […]

YouTube Bans True Crime Videos That Reanimate Dead Children With AI

In the age of the internet, even the most disturbing and grotesque content finds a platform, forcing companies like YouTube to tighten their policies in response to a surge in AI-generated videos depicting deceased minors and victims of violent events. This disturbing trend has sparked outrage and concern, prompting the need for clearer guidelines and […]

Masked Audio Generation using a Single Non-Autoregressive Transformer

We introduce MAGNeT, a masked generative sequence modeling method that operates directly over several streams of audio tokens. Unlike prior work, MAGNeT is comprised of a single-stage, non-autoregressive transformer. During training, we predict spans of masked tokens obtained from a masking scheduler, while during inference we gradually construct the output sequence using several decoding steps. […]

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

Source: Bytedance The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field. In this work, we introduce MagicVideo-V2 that integrates the text-to-image model, video motion generator, reference image embedding module and frame interpolation module into an end-to-end video generation pipeline. Benefiting from these architecture designs, MagicVideo-V2 can generate […]



Prompt Engineering Guides



©2024 The Horizon