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 ...

Probability underlies much of the modern world – an engineering professor explains how it actually works

Probability underpins AI, cryptography and statistics. However, as the philosopher Bertrand Russell said, “Probability is the ...

Lab-in-the-loop framework enables rapid evolution of complex multi-mutant proteins

The search space for protein engineering grows exponentially with complexity. A protein of just 100 amino acids has 20100 ...