Mingchen Li

Widely-used emoji embedding models show surprisingly severe biases in how they represent different skin tones, even compared to LLMs.

Ditch the slow external knowledge base: this new method bakes clinical knowledge directly into LLMs for lightning-fast, state-of-the-art healthcare predictions.

Users often dangerously misunderstand the true scope of authority they've granted to computer-use agents, even while recognizing abstract risks.