Azalia Mirhoseini

Continuous scoring from LLM-as-a-Verifier leads to state-of-the-art verification accuracy and improved sample efficiency in reinforcement learning tasks.

Stealth biases in language models can be reliably detected using a novel distillation technique that amplifies hidden signals, transforming bias detection into a practical tool.

Decentralized coordination in multi-agent systems can boost reasoning performance and cut costs by 50% in large language model applications.

Forget hand-crafted training data: TRACE automatically identifies and fixes LLM agent capability gaps by turning failure trajectories into targeted RL training environments.

Forget scaling compute – the future of AI hinges on a 1000x leap in energy efficiency via tight AI+Hardware co-design over the next decade.

Verification at test time can be a surprisingly effective alternative to scaling policy learning for vision-language-action alignment, yielding substantial gains in both simulated and real-world robotic tasks.