LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Quiescent galaxies cluster more strongly than star-forming ones by 0.5-1 dex after halo-mass matching, with one-halo conformity up to z~2 that disappears at higher redshifts.
Hyrax is a GPU-enabled open-source framework for the full ML lifecycle in astronomy, with demonstrations of unsupervised discovery and classification on real survey data from Rubin, ZTF, and other projects.
SSL model detects galaxy interaction signatures with recall 0.86 and low contamination while CAS at A>0.35 has recall 0.20 but higher precision, benchmarked on visual classification of 25.1% disturbed fraction.
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.
citing papers explorer
-
One Generator, Any Process: LLM-Conditioning for the LHC
LLM embeddings condition a generative transformer to enable faster convergence, better performance, and generalization to unseen LHC processes using a single model.
-
COSMOS-Web: does halo mass alone shape the clustering of star-forming and quiescent galaxies?
Quiescent galaxies cluster more strongly than star-forming ones by 0.5-1 dex after halo-mass matching, with one-halo conformity up to z~2 that disappears at higher redshifts.
-
Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid
Hyrax is a GPU-enabled open-source framework for the full ML lifecycle in astronomy, with demonstrations of unsupervised discovery and classification on real survey data from Rubin, ZTF, and other projects.
-
Comparison and verification methods to trace interaction-driven disturbances in galaxies
SSL model detects galaxy interaction signatures with recall 0.86 and low contamination while CAS at A>0.35 has recall 0.20 but higher precision, benchmarked on visual classification of 25.1% disturbed fraction.
-
Robustness Analysis of USmorph: II. Optimizing Feature Extraction, Dimensionality Reduction, and Clustering for Unsupervised Galaxy Morphology Classification
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.