Yee Whye Teh

Evolution strategies can optimize large language models for long-horizon tasks with minimal GPU resources, outperforming traditional reinforcement learning approaches.

Many autoformalisation systems exhibit a troubling tendency to "silently correct" invalid inputs into valid proofs, revealing a critical flaw in their design.

Achieving superior performance in linear inverse problems, EPS reduces denoiser evaluations by an order of magnitude compared to conventional methods.

Ditch the slow sampling dance of diffusion models: Variational Flow Maps let you condition image generation in a single pass by learning the right initial noise.