5 papers
Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining
Adam Ousherovitch, Yixin Wang
Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that generates the parameter trajec…
Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation
Adam Ousherovitch, Yixin Wang
Modern learning systems excel at interpolation but struggle to generalize to unseen tasks outside the training distribution's support. This failure occurs even in simple settings,…
Evaluation of 3D Counterfactual Brain MRI Generation
Pengwei Sun, Wei Peng, Lun Yu Li +2
Counterfactual generation offers a principled framework for simulating hypothetical changes in medical imaging, with potential applications in understanding disease mechanisms and…
Brain-Cognition Fingerprinting via Graph-GCCA with Contrastive Learning
Yixin Wang, Wei Peng, Yu Zhang +3
Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing…
Imputing Brain Measurements Across Data Sets via Graph Neural Networks
Yixin Wang, Wei Peng, Susan F. Tapert +2
Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models…