Lester Mackey

Data synergy can either amplify or diminish model performance, revealing that the right dataset combinations are crucial for optimal language model training.

Express achieves a groundbreaking reduction in approximation error and memory usage for causal attention, outperforming existing methods and enabling more efficient long-context language modeling.

Get faster convergence in entropy-regularized learning tasks: Kernel Thinning slashes the computational cost of Mean Field Langevin Dynamics while preserving its theoretical guarantees.