Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...
GitHub

Moshi: a speech-text foundation model for real time dialogue

Finally, the code for the web UI client used in the Moshi demo is provided in the client/ directory. If you want to fine tune Moshi, head out to kyutai-labs/moshi ...

Using bat speed, swing shape to find potential MLB breakout stars

How the swing metrics Bat Speed, Swing Tilt and Intercept Point can help identify potential breakout hitters for the 2026 season.

American Jordan Stolz speedskates to a third Olympic medal — silver this time

U.S. speedskater Jordan Stolz had a lot of hype accompanying him in these Winter Olympic Games. He's now got two gold medals, ...
InfoWorld

WinterTC: Write once, run anywhere (for real this time)

The unified JavaScript runtime standard is an idea whose time has come. Here’s an inside look at the movement for server-side JavaScript interoperability.