Paper-Conference

Infinite Neural Operators: Gaussian Processes on Functions
A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over …
Cite
Parameter Efficient Fine-tuning via Explained Variance Adaptation
Foundation models (FMs) are pre-trained on large-scale datasets and then fine-tuned for a specific downstream task. The most common …
Cite
Calibrated Physics-Informed Uncertainty Quantification
Neural PDEs have emerged as inexpensive surrogate models for numerical PDE solvers. While they offer efficient approximations, they …
Cite URL
Semantic Cross-Pose Correspondence from a Single Example
This article focuses on predicting how an object can be transformed to a semantically meaningful pose relative to another object, given …
Cite
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?
Cite URL
Learning Chaos In A Linear Way
Learning long-term behaviors in chaotic dynamical systems, such as turbulent flows and climate modelling, is challenging due to their …
PDF Cite
Guaranteed Prediction Sets for Functional Surrogate models
We propose a method for obtaining statistically guaranteed prediction sets for functional machine learning methods: surrogate models …
Cite URL
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current …
Cite
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is …
Cite
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Streaming Bayes GFlowNets
Bayes’ rule naturally allows for inference refinement in a streaming fashion, without the need to recompute posteriors from scratch …
Cite