InfoWorld

19 large language models for safety or danger

These new models are specially trained to recognize when an LLM is potentially going off the rails. If they don’t like how an interaction is going, they have the power to stop it. Of course, every ...
IEEE

Language-Conditioned Imitation Learning With Base Skill Priors Under Unstructured Data

Abstract: The growing interest in language-conditioned robot manipulation aims to develop robots capable of understanding and executing complex tasks, with the objective of enabling robots to ...
Nature

AI can write genomes — how long until it creates synthetic life?

The Evo2 genomic language model can generate short genome sequences, but scientists say further advances are needed to write ...
IEEE

Undefined-oriented Programming: Detecting and Chaining Prototype Pollution Gadgets in Node.js Template Engines for Malicious Consequences

Abstract: Prototype pollution is a type of recently-discovered, impactful vulnerability that affects JavaScript code. One important yet challenging research problem of prototype pollution is how to ...