🏢 ETH Zurich

BI-DiffSR, a novel binarized diffusion model, achieves high-quality image super-resolution with significantly reduced memory and computational costs, outperforming existing methods.

This paper presents a novel method to make black box neural networks intervenable using only a small validation set with concept labels, improving the effectiveness of concept-based interventions.

BetterDepth: A plug-and-play diffusion refiner boosts zero-shot monocular depth estimation by adding fine details while preserving accurate geometry.

This study solves a key challenge in neural network learning, deriving a closed-form expression for the Bayes-optimal test error of extensive-width networks with quadratic activation functions from qu…

MAXMINLCB, a novel game-theoretic algorithm, efficiently solves bandit problems with preference feedback over continuous domains, providing anytime-valid, rate-optimal regret guarantees.

D-AdaST: A novel distributed adaptive minimax optimization method achieves near-optimal convergence by tracking stepsizes, solving the inconsistency problem hindering existing adaptive methods.

This paper introduces a novel framework for evaluating the robustness of machine learning models when the true data distribution is only partially known. It defines a new risk measure (‘identifiable r…