Search Results for author:
Found 4 papers, 2 papers with code
SimBIG: Field-level Simulation-Based Inference of Galaxy Clustering
We demonstrate the robustness of our analysis by showcasing our ability to infer unbiased cosmological constraints from a series of test simulations that are constructed using different forward models than the one used in our training dataset.
AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models
We present AstroCLIP, a strategy to facilitate the construction of astronomical foundation models that bridge the gap between diverse observational modalities.
xVal: A Continuous Number Encoding for Large Language Models
Large Language Models have not yet been broadly adapted for the analysis of scientific datasets due in part to the unique difficulties of tokenizing numbers.
Neural Collapse in the Intermediate Hidden Layers of Classification Neural Networks
We examine a variety of network architectures, activations, and datasets, and demonstrate that some degree of (NC) emerges in most of the intermediate hidden layers of the network, where the degree of collapse in any given layer is typically positively correlated with the depth of that layer in the neural network.
